© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6125
    Prev
    Next
    INDEX
    Explanations

    website links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    www
    0.78
     www
    0.59
    是谁
    0.48
    ං
    0.48
    제의
    0.47
    гыз
    0.46
    COVERY
    0.46
    展開
    0.44
    WWW
    0.42
    ர்
    0.42
    POSITIVE LOGITS
     interleukin
    0.48
     miếng
    0.48
     phleg
    0.47
     tient
    0.47
     及び
    0.47
     televisão
    0.47
     äl
    0.46
    iferous
    0.46
    s
    0.45
     tycker
    0.45
    Activations Density 0.095%

    No Known Activations