© 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. 183920
    Prev
    Next
    INDEX
    Explanations

    accrued entertainment liabilities

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

    detailed sections or structure

    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
     supplementation
    0.47
     troughs
    0.46
     ৰ
    0.46
     flick
    0.45
    urt
    0.44
     shortfall
    0.44
     olie
    0.44
    휘
    0.44
     pohyb
    0.44
     imbalances
    0.44
    POSITIVE LOGITS
    Credentials
    0.50
    FileInputExcel
    0.48
     invitación
    0.48
     губерна
    0.48
    CommandLine
    0.47
    Expires
    0.47
    Cemento
    0.47
    Pointing
    0.47
    Calling
    0.46
    description
    0.46
    Activations Density 0.000%

    No Known Activations