© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108210
    Prev
    Next
    INDEX
    Explanations

    indicate how or roughly how

    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_31_width_262k_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
    modelLogin
    0.43
     Dat
    0.39
    잤
    0.38
    DataType
    0.37
     decom
    0.37
     পাকিস্তানিদের
    0.36
    usern
    0.36
     vanilla
    0.36
    粙
    0.36
     Zim
    0.36
    POSITIVE LOGITS
    RENCE
    0.55
    financed
    0.47
     SMITH
    0.45
     bourse
    0.45
    มิ
    0.44
    近年
    0.44
    यर
    0.42
     QTL
    0.42
     majeure
    0.41
    都
    0.41
    Activations Density 0.004%

    No Known Activations