© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93269
    Prev
    Next
    INDEX
    Explanations

    expanding coverage, strengthening response, efficient integrated, health care

    np_acts-logits-general · gemini-2.5-flash-lite

    text describing organizational missions, program objectives, and strategic initiatives in development and aid contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     training
    -0.82
    GLOBAL
    -0.82
    ılacak
    -0.80
     Toolkit
    -0.79
     Evaluación
    -0.79
    为何
    -0.79
     столь
    -0.77
    enneth
    -0.76
    ΕΛ
    -0.75
     project
    -0.74
    POSITIVE LOGITS
     buds
    0.88
     county
    0.86
    capac
    0.84
     government
    0.78
    zp
    0.78
     dein
    0.77
    zum
    0.77
    ificaciones
    0.75
     turquoise
    0.75
     diffraction
    0.74
    Activations Density 0.016%

    No Known Activations