© 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. 203605
    Prev
    Next
    INDEX
    Explanations

    card or article details

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

    questions and answers

    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
    ו
    0.54
    드
    0.51
    ુ
    0.50
     IRI
    0.50
    ो
    0.47
     REACH
    0.45
     TUT
    0.45
    ు
    0.45
    צא
    0.44
    O
    0.43
    POSITIVE LOGITS
    questions
    0.55
     poesia
    0.55
    quiz
    0.53
     quizzes
    0.52
    hyp
    0.49
     poesía
    0.49
     questionnaire
    0.49
    bibliothek
    0.49
     simulations
    0.48
    harris
    0.48
    Activations Density 0.000%

    No Known Activations