© 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. 222640
    Prev
    Next
    INDEX
    Explanations

    plans, emails, checkout for you

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

    language patterns

    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
    ವ
    0.44
    㸸
    0.43
    ORT
    0.42
    נד
    0.42
    拿下
    0.42
    ᐅ
    0.42
    NED
    0.41
    LIC
    0.41
    PRO
    0.40
    ナトリ
    0.39
    POSITIVE LOGITS
     yuè
    0.53
    >[</
    0.52
     japonais
    0.49
     dà
    0.49
     chinois
    0.49
     świet
    0.49
     châu
    0.47
    rceil
    0.46
     भावनात्मक
    0.46
     Yol
    0.46
    Activations Density 0.000%

    No Known Activations