© 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. 12915
    Prev
    Next
    INDEX
    Explanations

    Option 1:

    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
     thous
    0.35
     cuánto
    0.35
     rubles
    0.35
     taus
    0.35
    স্বাস্থ্য
    0.34
    ᆻ
    0.33
    ግብ
    0.32
     psychopath
    0.32
     hinzu
    0.31
     soziale
    0.31
    POSITIVE LOGITS
    ️⃣
    0.50
    да
    0.41
    ⃣
    0.41
    as
    0.41
    oc
    0.40
     của
    0.40
    ，
    0.40
    on
    0.39
     is
    0.39
    of
    0.39
    Activations Density 0.161%

    No Known Activations