© 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. 193499
    Prev
    Next
    INDEX
    Explanations

    profit from

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

    competitive intensity brokers provide large context window blend for analysis often track

    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
    ﺘ
    0.46
    eiro
    0.44
     missing
    0.44
     surpre
    0.44
     undisputed
    0.44
    یتی
    0.43
     goalt
    0.43
     apparence
    0.43
     apresentado
    0.43
    Ⴀ
    0.43
    POSITIVE LOGITS
     perpendicularly
    0.47
     Amal
    0.43
    SIX
    0.42
    !),
    0.41
     заранее
    0.41
     Помимо
    0.41
     Weigh
    0.40
     Enumer
    0.40
     xx
    0.40
     Jamaica
    0.40
    Activations Density 0.001%

    No Known Activations