© 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. 251244
    Prev
    Next
    INDEX
    Explanations

    legal guardian or parent

    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
    元
    0.47
    writes
    0.45
    ↵↵
    0.43
    pseud
    0.43
     \
    0.43
     satur
    0.43
    in
    0.42
     priv
    0.42
    guest
    0.42
    alphabet
    0.41
    POSITIVE LOGITS
     Chiến
    0.57
     切り
    0.54
    涞
    0.54
    कई
    0.52
    หลาย
    0.49
    देखो
    0.49
     रक
    0.49
     સમયે
    0.48
    Следу
    0.48
     हैरानी
    0.48
    Activations Density 0.001%

    No Known Activations