© 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. 180566
    Prev
    Next
    INDEX
    Explanations

    bibliographic data format |a |b |c

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

    significance, evaluation, multilingual

    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
     raised
    0.44
     sculpture
    0.44
     raise
    0.43
    細菌
    0.43
     troll
    0.42
     Paths
    0.42
     بالغ
    0.41
    燧
    0.40
    Built
    0.40
     glassware
    0.40
    POSITIVE LOGITS
    进步
    0.52
     comprends
    0.46
    eder
    0.46
    功效
    0.46
    夶
    0.45
    гія
    0.44
     collation
    0.44
    𝒑
    0.44
    फ्तार
    0.43
    ല്‍
    0.43
    Activations Density 0.001%

    No Known Activations