© 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. 137896
    Prev
    Next
    INDEX
    Explanations

    use of words

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

    timeline unlocks

    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
    䢎
    0.47
     യൂണി
    0.46
    Downward
    0.46
     }_{
    0.45
    وجه
    0.45
     mAh
    0.45
     MQ
    0.44
     महागठबंधन
    0.44
    Jenny
    0.44
    Tween
    0.44
    POSITIVE LOGITS
     have
    0.54
     amazingly
    0.53
    a
    0.53
     aphids
    0.51
     squirrels
    0.50
     accurately
    0.50
    ilmesi
    0.49
    š
    0.49
     amel
    0.49
     mism
    0.49
    Activations Density 0.001%

    No Known Activations