© 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. 1245
    Prev
    Next
    INDEX
    Explanations

    as a character

    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
     Hock
    0.99
    貽
    0.96
     econometric
    0.88
     Romney
    0.77
    .$-
    0.75
    坭
    0.74
    )}-\
    0.73
     RECEIPTS
    0.72
    }$-(
    0.72
     Lynne
    0.70
    POSITIVE LOGITS
    Potion
    2.34
     armor
    2.27
     personnage
    2.24
    minecraft
    2.24
     minecraft
    2.22
    Fantasy
    2.21
    realm
    2.21
    fantasy
    2.19
    Elemental
    2.16
     fantasy
    2.11
    Activations Density 6.143%

    No Known Activations