© 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. 179611
    Prev
    Next
    INDEX
    Explanations

    relevant trade

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

    virtual or specific followed by nouns

    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
     accelerator
    0.47
    s
    0.47
     accelerating
    0.46
     trauma
    0.43
    目标
    0.42
     juvenile
    0.41
     తనకు
    0.41
     accelerators
    0.41
    stone
    0.40
     Levin
    0.40
    POSITIVE LOGITS
     भारतीय
    0.54
     donnant
    0.52
     ਪ
    0.51
     nuestras
    0.50
     prévoir
    0.49
     または
    0.48
    西班牙
    0.48
     ભાર
    0.47
    付属
    0.47
     ഭാ
    0.46
    Activations Density 0.000%

    No Known Activations