© 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. 109783
    Prev
    Next
    INDEX
    Explanations

    haunted him, want to, appearing in

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

    between languages and concepts

    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
    .
    0.46
    urement
    0.45
     situation
    0.43
    '
    0.43
     silos
    0.41
    _
    0.40
     ju
    0.40
     fitness
    0.40
     ore
    0.40
     annex
    0.40
    POSITIVE LOGITS
    ৮
    0.53
    лена
    0.53
     વર્ષ
    0.51
    ل
    0.51
    ת
    0.51
     માતા
    0.49
    ৯
    0.49
    АТ
    0.49
     процен
    0.49
    купно
    0.49
    Activations Density 0.000%

    No Known Activations