© 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. 29347
    Prev
    Next
    INDEX
    Explanations

    and followed by an outcome

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

    potential states and changes

    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
    ли
    0.57
    criminals
    0.50
    о
    0.49
    ве
    0.46
    pre
    0.46
     프로그램을
    0.46
    preferences
    0.45
    mov
    0.44
    Ли
    0.44
    clientes
    0.44
    POSITIVE LOGITS
     สูตร
    0.58
     dédiée
    0.53
     rameaux
    0.50
    的表现
    0.50
     workable
    0.48
    弟
    0.48
    转身
    0.48
     retorna
    0.47
    详解
    0.47
     suivie
    0.46
    Activations Density 0.000%

    No Known Activations