© 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. 128685
    Prev
    Next
    INDEX
    Explanations

    chosen to

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

    too much

    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
     caucasian
    0.45
     Caucasian
    0.45
     anillos
    0.45
     cabelos
    0.45
     gzip
    0.44
     &&
    0.43
     cheveux
    0.43
     Гинд
    0.42
     Cache
    0.42
    缓存
    0.42
    POSITIVE LOGITS
    which
    0.45
    भाग्य
    0.45
    𝐭
    0.43
    しまい
    0.42
    kosten
    0.41
    ٹ
    0.41
    𝐰
    0.40
    <0xD8>
    0.40
    costs
    0.39
    稱為
    0.39
    Activations Density 0.001%

    No Known Activations