© 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. 14531
    Prev
    Next
    INDEX
    Explanations

    public sector undertakings

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

    foreign characters and symbols

    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
    ገድ
    0.44
    何か
    0.44
    very
    0.42
    ೭
    0.42
    ขึ้น
    0.42
     كتبت
    0.41
    म्मेदारी
    0.41
    勝利
    0.41
    валися
    0.41
    coffee
    0.40
    POSITIVE LOGITS
     millennia
    0.44
     Mix
    0.40
    asic
    0.40
     interchangeably
    0.39
     Originals
    0.39
    徽
    0.38
     identically
    0.38
    丘
    0.38
     Positions
    0.38
     Plain
    0.38
    Activations Density 0.000%

    No Known Activations