© 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. 70615
    Prev
    Next
    INDEX
    Explanations

    professional or duration

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

    self-reliance leather depending

    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
    deficient
    0.50
    λεσ
    0.45
    ὗ
    0.43
    置
    0.42
    りと
    0.41
    সীম
    0.41
    কেলে
    0.40
    โ
    0.39
    前記
    0.39
    elif
    0.38
    POSITIVE LOGITS
     Hayley
    0.44
     sincerely
    0.42
     baseado
    0.41
     nyt
    0.40
     து
    0.39
    谆
    0.39
     Gen
    0.39
     gere
    0.39
     Sire
    0.39
     speakers
    0.38
    Activations Density 0.000%

    No Known Activations