© 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. 234223
    Prev
    Next
    INDEX
    Explanations

    foreign words and technical terms

    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
    ånd
    0.47
    electron
    0.45
    trunk
    0.43
    scatter
    0.42
    nextLine
    0.42
    оні
    0.41
    னை
    0.40
    ↝
    0.40
    indent
    0.40
    appeared
    0.39
    POSITIVE LOGITS
     Effekt
    0.58
     klasik
    0.54
     ingresso
    0.52
     generals
    0.49
     Ergebnis
    0.49
     Klan
    0.48
     Deadline
    0.48
    طبق
    0.47
     Kons
    0.47
     Klass
    0.47
    Activations Density 0.000%

    No Known Activations