© 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. 66756
    Prev
    Next
    INDEX
    Explanations

    questions and answers

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

    cases, questions

    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
     زر
    0.49
    Hz
    0.49
    㛣
    0.48
    Away
    0.47
    ]];
    0.46
     inoltre
    0.46
    (";
    0.46
    Control
    0.46
     الكهرب
    0.46
    {@
    0.45
    POSITIVE LOGITS
     asking
    0.53
    asking
    0.50
    asked
    0.50
     explosive
    0.46
     chiesto
    0.46
    問
    0.46
     vragen
    0.45
     पूछी
    0.45
     examen
    0.44
     menjawab
    0.44
    Activations Density 0.001%

    No Known Activations