© 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. 112345
    Prev
    Next
    INDEX
    Explanations

    days, administer, team

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

    specific situations or contexts

    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
     is
    0.47
     pä
    0.46
     dibut
    0.46
     När
    0.42
     aikana
    0.42
     Vil
    0.42
     paraffin
    0.41
    )
    0.41
     PBC
    0.40
     !$
    0.40
    POSITIVE LOGITS
     цель
    0.55
    OutputFile
    0.55
     Евге
    0.50
     REGIUNI
    0.46
    岘
    0.46
    InOut
    0.46
    ⵢ
    0.46
    럇
    0.46
     великолеп
    0.46
     дори
    0.45
    Activations Density 0.001%

    No Known Activations