© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 137174
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases after keywords

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

    specific entities or resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    瓣
    0.48
     Curso
    0.48
     ciência
    0.47
     JUSTICE
    0.47
     hiểm
    0.46
     NATURAL
    0.46
    裙
    0.46
     espaço
    0.46
     बाग
    0.45
     SCIENCE
    0.44
    POSITIVE LOGITS
    vel
    0.56
    Plasma
    0.55
    da
    0.50
    Penalty
    0.50
    plasma
    0.49
    a
    0.49
    instit
    0.49
    High
    0.48
    os
    0.48
    blas
    0.48
    Activations Density 0.000%

    No Known Activations