© 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. 139415
    Prev
    Next
    INDEX
    Explanations

    diagrams and measurements

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

    how serious they might be

    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
     АК
    0.48
     Иванович
    0.46
     И
    0.46
     Льво
    0.46
    мом
    0.46
    జేపీ
    0.46
    ника
    0.45
    Ц
    0.45
     Pryor
    0.45
    绕
    0.44
    POSITIVE LOGITS
    adecimal
    0.54
    diagram
    0.51
    ngram
    0.51
     diagrams
    0.49
    Diagram
    0.48
    agian
    0.48
    aziland
    0.47
    sized
    0.46
     prosedur
    0.46
     Diagram
    0.46
    Activations Density 0.001%

    No Known Activations