© 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. 155309
    Prev
    Next
    INDEX
    Explanations

    achieving pupils

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

    describes continuations or consequences

    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
     a
    0.45
     والج
    0.45
    li
    0.44
     spectroscopy
    0.44
     decomposition
    0.44
     crevices
    0.44
    ņu
    0.42
     mismatch
    0.42
     related
    0.42
     induced
    0.41
    POSITIVE LOGITS
    办法
    0.47
    그러나
    0.46
    চৈত
    0.46
    梆
    0.45
    旄
    0.45
    猢
    0.45
    මුත්
    0.44
    揍
    0.44
     Agricult
    0.44
     Nhưng
    0.43
    Activations Density 0.001%

    No Known Activations