© 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. 113547
    Prev
    Next
    INDEX
    Explanations

    easily manipulate

    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
    k
    0.57
    g
    0.55
    d
    0.53
    קי
    0.51
    ne
    0.47
    ज
    0.47
    st
    0.46
    ri
    0.46
    distances
    0.45
    ਗ
    0.45
    POSITIVE LOGITS
     بدا
    0.49
     økonom
    0.47
     spielte
    0.46
     教え
    0.45
    ેચ્છ
    0.45
     غير
    0.44
    řad
    0.44
     chợ
    0.43
     చేశాడు
    0.43
     LinearLayout
    0.43
    Activations Density 0.003%

    No Known Activations