© 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. 27306
    Prev
    Next
    INDEX
    Explanations

    in fact,

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

    Intelligence is complex

    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
    檢查
    0.45
    ັ້ງ
    0.45
    getType
    0.44
    зульта
    0.44
    いない
    0.44
    <0xA5>
    0.42
    苌
    0.41
     subtype
    0.41
    ത്മ
    0.41
    蔔
    0.41
    POSITIVE LOGITS
     أق
    0.48
     Lanka
    0.46
    edict
    0.44
     inférieure
    0.41
     countrymen
    0.41
     gering
    0.41
     οι
    0.41
     minore
    0.41
     inférieures
    0.41
    HEAP
    0.41
    Activations Density 0.000%

    No Known Activations