© 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. 135577
    Prev
    Next
    INDEX
    Explanations

    estimated times

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

    or, axis, population, parameter

    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
    สต
    0.55
    Ἐ
    0.54
    리로
    0.48
     následuj
    0.47
    dessä
    0.47
    Следу
    0.47
    клар
    0.46
    ற்
    0.46
    éb
    0.46
    Przyp
    0.46
    POSITIVE LOGITS
     appeals
    0.45
     Cooley
    0.44
     Reuters
    0.43
     vanadium
    0.43
    <0x0D>
    0.43
     ostensibly
    0.43
    arxiv
    0.43
     pharma
    0.43
     Website
    0.42
     /**
    0.42
    Activations Density 0.001%

    No Known Activations