© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163140
    Prev
    Next
    INDEX
    Explanations

    potential risks

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

    expands prompts, aims for distinct styles

    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
    ong
    0.54
    rpc
    0.54
    leng
    0.48
    ời
    0.48
    n
    0.47
     CDF
    0.44
    ig
    0.44
    ang
    0.44
    urry
    0.44
     grammar
    0.43
    POSITIVE LOGITS
    𝘔
    0.59
    अधिकांश
    0.57
    Representatives
    0.56
    𝙷
    0.54
    Ꮞ
    0.54
    Enlaces
    0.53
    এটি
    0.53
    光的
    0.53
    மய
    0.52
    VEY
    0.51
    Activations Density 0.001%

    No Known Activations