© 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. 175222
    Prev
    Next
    INDEX
    Explanations

    troubleshooting and user settings

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

    started phrases, items, or conditions

    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
    ो
    0.51
    ห
    0.44
    roke
    0.42
    로
    0.42
    ौ
    0.42
    chart
    0.42
    hir
    0.42
    า
    0.42
    tor
    0.41
    рован
    0.41
    POSITIVE LOGITS
    鸡蛋
    0.49
     يجب
    0.46
    এটা
    0.43
     друз
    0.43
    一般来说
    0.42
     Alongside
    0.41
     apricots
    0.40
     marshmallows
    0.40
     Nulla
    0.40
     kvůli
    0.40
    Activations Density 0.000%

    No Known Activations