© 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. 57500
    Prev
    Next
    INDEX
    Explanations

    roles or special interests

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

    Administrative Area

    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
    醎
    0.52
    ěji
    0.50
    tAux
    0.50
     ausführ
    0.50
    徝
    0.49
    rodu
    0.48
    >]</
    0.48
    čila
    0.48
    isers
    0.47
    raged
    0.47
    POSITIVE LOGITS
    OP
    0.49
    0.48
    Economic
    0.47
    OR
    0.45
    Tipo
    0.44
     sulfuric
    0.43
     estaba
    0.42
    C
    0.41
    Protocol
    0.41
    Hmm
    0.41
    Activations Density 0.000%

    No Known Activations