© 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. 37172
    Prev
    Next
    INDEX
    Explanations

    documentary offering, cause, helped, directly made

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

    reward, kiosk, crispy, HC, days

    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
    ิ
    0.57
    ナナ
    0.52
    س
    0.52
     корректи
    0.48
     i
    0.48
     recrut
    0.48
    ジ
    0.48
    वीण
    0.48
     aux
    0.48
     recevoir
    0.48
    POSITIVE LOGITS
    Order
    0.46
    शील
    0.45
    _->
    0.43
    ﻛ
    0.42
    Loss
    0.42
     griech
    0.42
    isComposite
    0.41
    ~(\
    0.41
     hukum
    0.41
    getItemId
    0.40
    Activations Density 0.001%

    No Known Activations