© 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. 67499
    Prev
    Next
    INDEX
    Explanations

    money and time sequences

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

    while/if followed by a suggestion or future

    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
     Cast
    0.50
    ,
    0.50
     Tales
    0.48
     Mari
    0.46
     .
    0.46
     Kathryn
    0.46
    ate
    0.45
     Merry
    0.45
     Radical
    0.45
     Met
    0.45
    POSITIVE LOGITS
     pourraient
    0.50
     nėra
    0.49
    슝
    0.48
     advantages
    0.48
     retorn
    0.48
     mniej
    0.47
     conforman
    0.47
     proposent
    0.47
    hör
    0.46
     vantagem
    0.46
    Activations Density 0.001%

    No Known Activations