© 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. 49072
    Prev
    Next
    INDEX
    Explanations

    each paragraph

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

    historical context and background

    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
    لاف
    0.48
     immobili
    0.46
    ffici
    0.45
    ন্দ
    0.45
    ા
    0.44
     темы
    0.43
     narratives
    0.42
     alimentaire
    0.42
    இ
    0.42
    გორ
    0.42
    POSITIVE LOGITS
     ሶ
    0.51
     crainte
    0.47
    yan
    0.46
    FAI
    0.46
     sogno
    0.45
     padassa
    0.44
     benutzer
    0.44
    INCREMENT
    0.43
     caoutch
    0.43
     باسکٹ
    0.43
    Activations Density 0.000%

    No Known Activations