© 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. 245716
    Prev
    Next
    INDEX
    Explanations

    news COMPANY

    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
    hypothesis
    0.44
     neut
    0.43
    Faction
    0.43
    speaker
    0.42
    given
    0.42
    امت
    0.41
    ే
    0.41
    تاب
    0.41
    continuous
    0.41
    speakers
    0.40
    POSITIVE LOGITS
    UTURE
    0.52
     ಉಳ
    0.47
    剰
    0.46
     ಕಂಚ
    0.46
     компания
    0.46
     कम्पनी
    0.45
    COMPANY
    0.45
     ንጥረ
    0.45
    <unused2140>
    0.45
     компанию
    0.45
    Activations Density 0.001%

    No Known Activations