© 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. 2885
    Prev
    Next
    INDEX
    Explanations

    opening quotation mark and following word

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

    opening quotes followed by text

    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
     kaa
    0.45
     ayatan
    0.44
     squiggle
    0.44
    <unused94>
    0.42
     komma
    0.42
     quantos
    0.42
     antlers
    0.42
     prothorax
    0.41
     አይደ
    0.40
     meatballs
    0.40
    POSITIVE LOGITS
    This
    0.54
    The
    0.52
    Despite
    0.49
    A
    0.48
    Although
    0.48
    While
    0.44
    ,
    0.44
     This
    0.43
    We
    0.43
    In
    0.42
    Activations Density 0.057%

    No Known Activations