© 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. 191488
    Prev
    Next
    INDEX
    Explanations

    playback offline

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

    seeking information

    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
     abordagem
    0.55
    وير
    0.46
     parceria
    0.43
    航
    0.43
    সময়
    0.43
    )')
    0.42
    حث
    0.41
    Melitaea
    0.41
    滘
    0.41
     filede
    0.41
    POSITIVE LOGITS
    ICK
    0.47
    ה
    0.46
    \]
    0.46
     היא
    0.45
    ษ
    0.45
     indis
    0.44
     продукт
    0.44
     לר
    0.43
     സമ്പ
    0.43
     incontro
    0.43
    Activations Density 0.001%

    No Known Activations