© 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. 76963
    Prev
    Next
    INDEX
    Explanations

    defining operations and outcomes

    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
    Fb
    0.48
     aj
    0.47
    bera
    0.46
     offenen
    0.45
     Flü
    0.44
     problémy
    0.43
    ܀
    0.43
     వ్యా
    0.43
    មា
    0.43
     credito
    0.43
    POSITIVE LOGITS
     six
    0.47
     Republican
    0.46
     छह
    0.45
    ੱਕ
    0.44
    بازی
    0.43
     ಕಾಂಗ್ರೆ
    0.42
     UVB
    0.42
    हालांकि
    0.41
    </em>
    0.41
    tokenize
    0.41
    Activations Density 0.001%

    No Known Activations