© 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. 1643
    Prev
    Next
    INDEX
    Explanations

    generate image

    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
    .—
    1.49
     reckons
    1.40
     Bride
    1.38
    &-
    1.34
     envis
    1.29
     bà
    1.29
     Tipp
    1.28
     Lank
    1.28
     Bamber
    1.27
    .|
    1.26
    POSITIVE LOGITS
     a
    1.83
     luxury
    1.81
     undefined
    1.68
    6
    1.68
    7
    1.61
     inanimate
    1.60
    4
    1.54
    mapsto
    1.54
     classes
    1.52
     conductivity
    1.50
    Activations Density 0.503%

    No Known Activations