© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 88615
    Prev
    Next
    INDEX
    Explanations

    pictures and shows

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

    contrasting ideas or consequences

    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
    在了
    0.46
     entirety
    0.45
    忱
    0.44
     collapsed
    0.44
    াহরণ
    0.42
    ľa
    0.42
    yclerView
    0.42
     lệch
    0.42
    ρυ
    0.41
     skipped
    0.41
    POSITIVE LOGITS
     NCA
    0.45
    <
    0.44
     लैस
    0.44
     உடைய
    0.42
    weza
    0.42
     McM
    0.41
     McD
    0.41
    Cad
    0.41
     경영
    0.41
     приез
    0.40
    Activations Density 0.002%

    No Known Activations