© 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. 56919
    Prev
    Next
    INDEX
    Explanations

    plans on / it would / love wins

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

    conversational phrases with context

    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
    UTO
    0.47
     correlate
    0.45
    чил
    0.45
    जील
    0.45
    雫
    0.44
    WARD
    0.43
    UART
    0.43
    도로
    0.43
     THINK
    0.43
    ವಾಡ
    0.43
    POSITIVE LOGITS
     Solicitors
    0.52
    ,\,
    0.46
    ik
    0.44
     actriz
    0.44
    ,_
    0.44
    iros
    0.44
     solicitors
    0.44
    ,//
    0.44
     jeste
    0.43
     barrister
    0.43
    Activations Density 0.000%

    No Known Activations