© 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. 197652
    Prev
    Next
    INDEX
    Explanations

    metalcasting

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

    list or bullet item start

    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
     事業
    0.45
     ats
    0.43
     Knud
    0.43
    imbangan
    0.43
     teh
    0.42
    ?
    0.42
     prestigio
    0.41
    ẳn
    0.41
    ...\...\
    0.41
     infine
    0.41
    POSITIVE LOGITS
    entiti
    0.47
    ért
    0.46
    িলা
    0.45
    ம்
    0.45
     বাসা
    0.45
    ت
    0.45
     जैन
    0.43
    ielles
    0.43
    ט
    0.43
    মত
    0.43
    Activations Density 0.000%

    No Known Activations