© 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. 203862
    Prev
    Next
    INDEX
    Explanations

    Lobby Reception

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

    how bots work

    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
     ഒറ്റ
    0.57
     গভর্ন
    0.56
     வேளா
    0.53
     জনসাধারণ
    0.51
    chränk
    0.51
    鄀
    0.51
     ইন্দ
    0.50
     গুরুতর
    0.49
     dễ
    0.49
     nếu
    0.48
    POSITIVE LOGITS
    ↵
    0.60
     exposition
    0.43
    <b>
    0.42
     pause
    0.42
     charged
    0.41
    section
    0.41
    cover
    0.41
    surprise
    0.41
    apest
    0.40
     nostalg
    0.40
    Activations Density 0.000%

    No Known Activations