© 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. 24798
    Prev
    Next
    INDEX
    Explanations

    pointer dereference then variable

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

    collections of items

    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
    hto
    0.49
    pesar
    0.48
     clung
    0.48
    venuti
    0.46
    []
    0.46
     one
    0.44
    bej
    0.43
    cento
    0.43
    rensa
    0.43
    ژه
    0.43
    POSITIVE LOGITS
    การ
    0.54
     Antibodies
    0.46
    汔
    0.45
    రిక
    0.44
    ీ
    0.44
    Optimization
    0.43
    ే
    0.43
    ATORY
    0.43
    萏
    0.43
    า
    0.43
    Activations Density 0.000%

    No Known Activations