© 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-65K
    7. 16933
    Prev
    Next
    INDEX
    Explanations

    frequency, accounting, or medical terms

    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_65k_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
    ^(-
    0.46
     ≥
    0.45
     cosmological
    0.45
     fag
    0.42
    ૃત
    0.42
     handball
    0.41
     ফ্র
    0.41
    <%=
    0.41
    න
    0.40
     red
    0.40
    POSITIVE LOGITS
     insulate
    0.45
    etzen
    0.45
    zied
    0.44
    quart
    0.42
    vä
    0.42
     चौथ
    0.42
     Elke
    0.41
     verwendet
    0.41
     доли
    0.41
     Kollegen
    0.41
    Activations Density 0.035%

    No Known Activations