© 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-262K
    7. 113191
    Prev
    Next
    INDEX
    Explanations

    served with

    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_262k_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
    in
    0.58
    y
    0.44
    throat
    0.44
    ៊ី
    0.44
    therm
    0.43
    imp
    0.43
    worst
    0.42
     Sticks
    0.42
     sus
    0.42
    depend
    0.42
    POSITIVE LOGITS
     pracy
    0.51
    ністю
    0.50
     thuyền
    0.50
     máy
    0.49
     έργ
    0.48
    Ấ
    0.48
     tấn
    0.48
     lifeboat
    0.47
     trabalhos
    0.47
     галакти
    0.47
    Activations Density 0.003%

    No Known Activations