© 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. 17982
    Prev
    Next
    INDEX
    Explanations

    arrived is in sauce

    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
     નવી
    0.49
    formul
    0.48
     ഇതി
    0.46
    多様
    0.45
     tantôt
    0.45
     રિ
    0.45
    齦
    0.45
    ینه
    0.44
    جہ
    0.44
     జన
    0.44
    POSITIVE LOGITS
    in
    0.49
    is
    0.47
    e
    0.46
    a
    0.46
    i
    0.46
    u
    0.43
    il
    0.41
    Opens
    0.41
    //
    0.41
     class
    0.40
    Activations Density 0.001%

    No Known Activations