© 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. 7632
    Prev
    Next
    INDEX
    Explanations

    Eidolon V you wide

    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
     tropas
    0.66
    /
    0.64
     típ
    0.59
     blobs
    0.56
     tannins
    0.53
     erections
    0.52
     riffs
    0.52
     troughs
    0.52
    い
    0.52
     uptime
    0.52
    POSITIVE LOGITS
    how
    0.63
    tidak
    0.63
    ha
    0.54
    hr
    0.52
    cough
    0.52
    not
    0.51
    know
    0.51
    por
    0.51
    prima
    0.51
    
    0.51
    Activations Density 0.588%

    No Known Activations