© 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. 240529
    Prev
    Next
    INDEX
    Explanations

    able to do

    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
    mlp
    0.45
    prettier
    0.43
    ,
    0.42
    mover
    0.42
    magnet
    0.42
    schema
    0.42
    decay
    0.42
     disson
    0.41
    %%
    0.41
    nice
    0.41
    POSITIVE LOGITS
     सदस्यीय
    0.56
     रहेगी
    0.46
     Při
    0.46
    abilität
    0.46
    㶱
    0.45
     Aku
    0.45
    为你
    0.44
    诃
    0.44
    挍
    0.44
    敚
    0.44
    Activations Density 0.000%

    No Known Activations