© 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. 244137
    Prev
    Next
    INDEX
    Explanations

    vocational counselor

    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
    MARK
    0.49
    wegen
    0.48
    anticipated
    0.47
    steering
    0.46
    記念
    0.46
    caution
    0.45
    過
    0.45
    of
    0.44
    rush
    0.44
    ゴン
    0.44
    POSITIVE LOGITS
     hiểu
    0.45
     содержимое
    0.43
    fillStyle
    0.43
    examtype
    0.43
    ৤
    0.42
     слой
    0.42
     내용은
    0.41
    êle
    0.41
     ھ
    0.41
     sax
    0.41
    Activations Density 0.001%

    No Known Activations