© 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. 221830
    Prev
    Next
    INDEX
    Explanations

    speech writer

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

    abbreviations and numerals

    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
     Partei
    0.58
    C
    0.54
    Parte
    0.50
    The
    0.49
    E
    0.49
    Hann
    0.48
    Estimated
    0.47
     Handler
    0.46
     Před
    0.46
     Parte
    0.46
    POSITIVE LOGITS
     metavar
    0.55
     choker
    0.50
     جذاب
    0.48
     variegated
    0.46
     되는
    0.45
    patial
    0.43
    ঞ্
    0.43
    )|\
    0.42
    িকারী
    0.42
    rious
    0.42
    Activations Density 0.002%

    No Known Activations