© 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. 209883
    Prev
    Next
    INDEX
    Explanations

    dotted or hyphenated words

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

    threats and punishment

    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
     प्रतिकूल
    0.46
     televisión
    0.46
     estaba
    0.44
     yılında
    0.43
     भन्ने
    0.43
     televisie
    0.43
     टेलीविजन
    0.42
    
    0.42
     sitios
    0.42
     refleja
    0.42
    POSITIVE LOGITS
     Hand
    0.43
     specifically
    0.43
    も
    0.43
    ONT
    0.42
    我说
    0.41
     and
    0.40
    ont
    0.40
     hand
    0.40
     Crib
    0.39
     speaking
    0.39
    Activations Density 0.001%

    No Known Activations