© 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. 87963
    Prev
    Next
    INDEX
    Explanations

    technical terms and standards

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

    detailed breakdown

    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
    лаве
    0.53
    áva
    0.52
    áus
    0.52
    ковь
    0.52
    尌
    0.52
    ныгы
    0.50
     เต็ม
    0.50
     bestaat
    0.50
    桻
    0.49
     આજ
    0.48
    POSITIVE LOGITS
     cancers
    0.47
     superimposed
    0.47
    /
    0.47
    salmon
    0.46
    Stevens
    0.46
    ｓ
    0.45
     slaughter
    0.44
     or
    0.43
     tasso
    0.43
     salmon
    0.43
    Activations Density 0.000%

    No Known Activations