© 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. 997
    Prev
    Next
    INDEX
    Explanations

    the skillet

    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
     separar
    0.65
     unabhäng
    0.65
    rinsic
    0.65
    epin
    0.64
     Gründung
    0.62
    Depends
    0.61
     )
    0.60
    "):
    0.59
     букмекерлик
    0.59
    쭤
    0.57
    POSITIVE LOGITS
     Romney
    1.44
     Mc
    1.33
     Gaff
    1.32
     impressively
    1.32
     Krom
    1.31
     UAE
    1.28
     Pak
    1.26
    Pak
    1.25
     mort
    1.25
     likewise
    1.23
    Activations Density 0.296%

    No Known Activations