© 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. 72549
    Prev
    Next
    INDEX
    Explanations

    SEE MORE

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

    illegality of unauthorized keys

    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
    𝘇
    0.47
     всё
    0.46
    rés
    0.46
    destino
    0.46
    context
    0.46
    agreement
    0.45
     फें
    0.45
     realtime
    0.45
    examin
    0.45
     overly
    0.44
    POSITIVE LOGITS
    خ
    0.45
     Veter
    0.44
    जनिक
    0.44
    gey
    0.42
    जनक
    0.42
     Veterinary
    0.41
    س
    0.41
     ena
    0.41
    তি
    0.41
    urian
    0.40
    Activations Density 0.001%

    No Known Activations