© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16095
    Prev
    Next
    INDEX
    Explanations

    cabinet, prints, sunrise, abstract

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

    function parameter documentation

    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_16k_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
    Cov
    0.45
    방
    0.43
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.43
    ecta
    0.42
    itura
    0.42
    ────────────────
    0.42
     (†
    0.42
    한
    0.42
     ⇒
    0.41
    ...');
    0.41
    POSITIVE LOGITS
     liquides
    0.47
     materias
    0.46
     gases
    0.44
     cardiop
    0.43
     autos
    0.43
     assunto
    0.43
     componentes
    0.43
     donnée
    0.43
     coul
    0.43
     container
    0.42
    Activations Density 0.000%

    No Known Activations