© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3211
    Prev
    Next
    INDEX
    Explanations

    object method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ปก
    0.41
    蝙
    0.40
    飏
    0.38
    دد
    0.38
    arsanız
    0.38
    क्षम
    0.37
    パナソニック
    0.37
    ธ
    0.37
    谔
    0.36
     рэгістра
    0.36
    POSITIVE LOGITS
    get
    0.82
    toString
    0.71
    tolist
    0.68
     get
    0.67
    astype
    0.64
    ToString
    0.58
     __
    0.57
     clone
    0.57
     toString
    0.56
    replace
    0.55
    Activations Density 0.091%

    No Known Activations