© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138098
    Prev
    Next
    INDEX
    Explanations

    in a way

    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_16_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
     infiltrating
    0.75
     penetrating
    0.72
     dividing
    0.70
     interrupting
    0.68
     pausing
    0.66
    .
    0.66
     captivating
    0.66
     disconnecting
    0.66
     brightly
    0.65
     facilitating
    0.65
    POSITIVE LOGITS
    Num
    0.69
    Hispanic
    0.68
    Mk
    0.66
    UY
    0.66
    FProperties
    0.66
    XY
    0.64
    R
    0.64
    F
    0.63
    MOS
    0.62
    C
    0.62
    Activations Density 0.004%

    No Known Activations