© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206901
    Prev
    Next
    INDEX
    Explanations

    track record

    np_acts-logits-general · gemini-2.5-flash-lite

    specific technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ">
    0.49
     ".
    0.48
    ,<
    0.46
    .<
    0.46
    .¹
    0.46
     "?"
    0.45
    ۔
    0.45
    Forum
    0.45
     darkly
    0.45
    |<
    0.44
    POSITIVE LOGITS
     estates
    0.48
    ᆺ
    0.44
    점
    0.43
     NEG
    0.43
     mandate
    0.43
     takeover
    0.42
     Neg
    0.41
     intake
    0.41
    经营
    0.40
    マル
    0.39
    Activations Density 0.000%

    No Known Activations