© 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. 58568
    Prev
    Next
    INDEX
    Explanations

    verb phrases

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

    conditional or technical language

    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
    ת
    0.53
    пів
    0.50
    これにより
    0.48
    proguard
    0.47
    валася
    0.47
    Haan
    0.46
    љи
    0.46
    薁
    0.45
    личи
    0.44
    意味着
    0.44
    POSITIVE LOGITS
     @
    0.60
     que
    0.52
     from
    0.50
     hoch
    0.47
     sehr
    0.47
    @
    0.46
     P
    0.46
    ogène
    0.46
     parte
    0.46
     sociedade
    0.46
    Activations Density 0.000%

    No Known Activations