© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 446
    Prev
    Next
    INDEX
    Explanations

    connecting phrases or clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Organisation
    1.87
    polyfills
    1.72
    icksburg
    1.69
    rež
    1.67
    statistic
    1.63
    捱
    1.61
    ioane
    1.60
    谚
    1.60
     料
    1.59
     Severn
    1.58
    POSITIVE LOGITS
    8
    1.82
    7
    1.78
    6
    1.71
    ebb
    1.38
    9
    1.35
     fucking
    1.35
     ballistic
    1.34
    5
    1.34
    采集
    1.30
    ६
    1.30
    Activations Density 0.073%

    No Known Activations