© 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. 168782
    Prev
    Next
    INDEX
    Explanations

    carrier liability and conditions

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

    Location, science, cheaply

    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
     ভোক
    0.44
     conceptos
    0.43
    urbo
    0.42
    i
    0.42
     debemos
    0.41
     lexical
    0.41
     دبستان
    0.41
     cursus
    0.40
    scoped
    0.40
     con
    0.40
    POSITIVE LOGITS
    龴
    0.50
     Straße
    0.48
    ണ്യ
    0.48
    vcn
    0.47
    zen
    0.46
     الأمن
    0.45
    軍
    0.44
    証明
    0.44
    運輸
    0.44
    astopol
    0.44
    Activations Density 0.000%

    No Known Activations