© 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. 1130
    Prev
    Next
    INDEX
    Explanations

    model following start of turn

    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
    铉
    1.04
     Nelson
    1.03
     varic
    0.99
     Wim
    0.99
    Nelson
    0.98
     metode
    0.97
     metodi
    0.97
     VON
    0.97
     Vik
    0.97
    Chile
    0.97
    POSITIVE LOGITS
     Penn
    1.03
    Penn
    0.96
     Cosmo
    0.82
     Phill
    0.74
    잔
    0.73
    abba
    0.73
     잔
    0.71
    Narr
    0.71
    idences
    0.71
     Phila
    0.70
    Activations Density 3.776%

    No Known Activations