© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1056
    Prev
    Next
    INDEX
    Explanations

    question starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    ’
    1.55
     to
    1.54
    '
    1.44
     of
    1.39
     (
    1.36
    inerary
    1.34
    led
    1.33
    (
    1.27
     with
    1.26
     is
    1.26
    POSITIVE LOGITS
     minecraft
    2.43
     combust
    2.25
    <unused505>
    2.21
    Diffuse
    2.21
     unoccupied
    2.20
    basketball
    2.19
    <unused1917>
    2.18
     desolate
    2.17
     streetwear
    2.17
     habitable
    2.17
    Activations Density 0.121%

    No Known Activations