© 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. 208642
    Prev
    Next
    INDEX
    Explanations

    foreign languages and proper names

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

    malware and piracy

    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
    лил
    0.51
    Drop
    0.46
     guitar
    0.45
     EDI
    0.43
    خدام
    0.43
    痔
    0.43
    Bathroom
    0.42
     parts
    0.41
    ならない
    0.41
    Sharing
    0.41
    POSITIVE LOGITS
    ר
    0.61
    בער
    0.57
     Sosa
    0.51
     Método
    0.50
     Decreto
    0.49
     Mittel
    0.47
     Truy
    0.46
     Aguas
    0.46
    ט
    0.46
    וני
    0.46
    Activations Density 0.000%

    No Known Activations