© 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. 178715
    Prev
    Next
    INDEX
    Explanations

    person, require, them, Osbourne, differentiation

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

    instructions numbered options

    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
     обычной
    0.53
     ደቂ
    0.48
     обращения
    0.48
     میتوان
    0.46
     λεπ
    0.46
    گ
    0.46
     feitos
    0.45
    Ми
    0.45
    ໃຫ
    0.45
    Ги
    0.44
    POSITIVE LOGITS
    3
    0.59
    2
    0.59
    in
    0.53
    satisfied
    0.52
    pickle
    0.49
    feather
    0.49
    edit
    0.48
    trimethyl
    0.48
     y
    0.47
    closure
    0.47
    Activations Density 0.000%

    No Known Activations