© 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. 564
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
     내용은
    2.24
     Vee
    2.09
    囝
    2.08
     adjournment
    1.98
     assuré
    1.97
     vaut
    1.97
    タック
    1.97
    dler
    1.97
     arrows
    1.94
     palin
    1.92
    POSITIVE LOGITS
     perceiving
    2.11
     who
    2.05
     którzy
    1.99
     inhabiting
    1.94
    7
    1.93
    들에게
    1.84
    6
    1.74
    8
    1.73
     kteří
    1.73
     kojima
    1.56
    Activations Density 0.884%

    No Known Activations