© 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. 1196
    Prev
    Next
    INDEX
    Explanations

    Get ready to embrace future pasta summaries

    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
    jn
    0.66
    vol
    0.59
    j
    0.56
    ajn
    0.54
    avo
    0.52
    ondas
    0.51
    aj
    0.50
    솟
    0.49
    avi
    0.49
     <
    0.48
    POSITIVE LOGITS
     epistle
    1.58
     Shire
    1.56
     Gamble
    1.56
     Gerry
    1.55
    Booth
    1.50
    明年
    1.49
    Ary
    1.49
     Philippines
    1.49
     poth
    1.48
    estabelecimento
    1.48
    Activations Density 0.120%

    No Known Activations