© 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. 11041
    Prev
    Next
    INDEX
    Explanations

    Fathom SD, Lary, AIG, Farmingdale, Kroger, Duality

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

    initial letters followed by specific completions

    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
    4
    1.16
    5
    0.96
    6
    0.95
    8
    0.89
    7
    0.87
    3
    0.86
    (
    0.73
    9
    0.72
    ید
    0.67
    ции
    0.63
    POSITIVE LOGITS
    that
    0.79
    ك
    0.64
    although
    0.57
    this
    0.56
    an
    0.55
    ia
    0.55
     Toutes
    0.55
    the
    0.54
    Is
    0.54
    first
    0.54
    Activations Density 0.311%

    No Known Activations