© 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. 241962
    Prev
    Next
    INDEX
    Explanations

    time, duration, or usage

    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
    gele
    0.46
    Physical
    0.46
    ב
    0.45
    Theorem
    0.44
     disprove
    0.44
    Buildings
    0.43
    mniejs
    0.42
    getpath
    0.42
     प्रत्ये
    0.42
    𝔯
    0.42
    POSITIVE LOGITS
     została
    0.51
     zostały
    0.51
     watersheds
    0.50
     nasze
    0.47
     această
    0.45
     git
    0.45
     counterparts
    0.44
     zac
    0.44
     MTS
    0.44
     koja
    0.44
    Activations Density 0.001%

    No Known Activations