© 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. 27046
    Prev
    Next
    INDEX
    Explanations

    time in sentence structure

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

    biological processes, attribution, or insurance

    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
    늪
    0.49
     будете
    0.47
     ছিলাম
    0.46
    는
    0.44
     WITH
    0.44
    тего
    0.43
     YOU
    0.41
     Елена
    0.41
    è
    0.41
     изначально
    0.40
    POSITIVE LOGITS
     troughs
    0.51
     apoptotic
    0.50
     starch
    0.48
     spermat
    0.47
     metastasis
    0.47
     parabol
    0.47
     glutamate
    0.47
     chemot
    0.45
    することができる
    0.45
     homot
    0.45
    Activations Density 0.000%

    No Known Activations