© 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. 92984
    Prev
    Next
    INDEX
    Explanations

    boundary", "ITUC", "freedom"

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    密
    -0.80
    englanniksi
    -0.73
    MATCH
    -0.71
    שב
    -0.70
    tagna
    -0.70
    чества
    -0.70
    硬件
    -0.70
    હે
    -0.70
     hakim
    -0.69
    าว
    -0.69
    POSITIVE LOGITS
    GRI
    1.02
     boundary
    0.90
    typen
    0.89
    嘮
    0.81
     vínculos
    0.80
    FormUrlEncoded
    0.80
    DMA
    0.79
    boundary
    0.78
     中村
    0.78
    Boundary
    0.77
    Activations Density 0.004%

    No Known Activations