© 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. 60030
    Prev
    Next
    INDEX
    Explanations

    numbers followed by names/locations

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

    related to command or action

    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
     ihres
    0.48
    recovered
    0.45
    recovery
    0.44
    ᱒
    0.44
    jera
    0.44
    reliant
    0.44
    career
    0.43
     ম্যানেজার
    0.42
     மிகப்பெ
    0.42
    他們的
    0.40
    POSITIVE LOGITS
    反对
    0.49
     нара
    0.48
    a
    0.48
    UMB
    0.47
     tabular
    0.46
     searchable
    0.45
     counterparts
    0.44
     ضمن
    0.44
     घटक
    0.44
     dayan
    0.43
    Activations Density 0.000%

    No Known Activations