© 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. 209010
    Prev
    Next
    INDEX
    Explanations

    company issues

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

    vertical lines and symbols

    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
     generations
    0.45
     barometer
    0.44
    x
    0.42
    ἃ
    0.41
     lac
    0.40
     fax
    0.40
    <0xE6>
    0.39
     profil
    0.39
     aspirations
    0.39
    <0xE3>
    0.39
    POSITIVE LOGITS
     تکلیف
    0.54
     تجهیز
    0.47
    amı
    0.46
    ಸು
    0.46
     کمان
    0.44
    aviti
    0.44
    انوي
    0.43
     آن
    0.43
    وجه
    0.43
     εν
    0.43
    Activations Density 0.001%

    No Known Activations