© 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. 41922
    Prev
    Next
    INDEX
    Explanations

    actions and consequences

    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
     v
    0.51
    msp
    0.48
    肉
    0.47
     '),
    0.46
    oil
    0.44
    onbury
    0.44
    ৫৫
    0.44
    ртка
    0.44
    選
    0.43
    v
    0.43
    POSITIVE LOGITS
     semicon
    0.49
     mécan
    0.48
     divergents
    0.47
     chercheurs
    0.46
     goles
    0.46
     Боль
    0.46
     pesquis
    0.46
     idempot
    0.46
     majeur
    0.45
     comportement
    0.45
    Activations Density 0.001%

    No Known Activations