© 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. 243636
    Prev
    Next
    INDEX
    Explanations

    disabled, of, securely, vacation, in, scale, meat, during, ,

    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
     puissant
    0.48
    тивний
    0.48
     aparentemente
    0.48
    тный
    0.47
    る
    0.47
    持ち
    0.46
     rép
    0.46
     subspaces
    0.46
     obchod
    0.46
    тельный
    0.46
    POSITIVE LOGITS
    GroupName
    0.47
    Pays
    0.47
    j
    0.46
    ’
    0.46
    Yaw
    0.45
    续
    0.45
    orat
    0.44
    '
    0.44
    Orth
    0.44
    statt
    0.43
    Activations Density 0.000%

    No Known Activations