© 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. 95917
    Prev
    Next
    INDEX
    Explanations

    various languages

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

    following punctuation or 'input'

    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
     File
    0.52
     I
    0.50
     Storage
    0.49
     Membrane
    0.48
     Vector
    0.48
     Nested
    0.48
     Salat
    0.47
     Dark
    0.46
     croup
    0.46
     Input
    0.45
    POSITIVE LOGITS
    kę
    0.56
    στι
    0.52
    ன்னு
    0.50
    ጧ
    0.50
     opportunità
    0.50
     mnie
    0.49
    ड
    0.49
     fırs
    0.49
    ouna
    0.49
    કસ
    0.49
    Activations Density 0.000%

    No Known Activations