© 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. 50536
    Prev
    Next
    INDEX
    Explanations

    yearly fee

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

    nestled securely, depends on

    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
    n
    0.55
    achi
    0.49
    結論
    0.46
    兵庫
    0.45
    ック
    0.45
    o
    0.44
     progresses
    0.44
    事務所
    0.44
    m
    0.44
    冠
    0.44
    POSITIVE LOGITS
     strobe
    0.51
     Schä
    0.50
     roto
    0.50
     Rotation
    0.49
     ülke
    0.48
     neglect
    0.47
    ɭ
    0.47
     কারও
    0.47
     vecteur
    0.47
     rotation
    0.47
    Activations Density 0.000%

    No Known Activations