© 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. 116931
    Prev
    Next
    INDEX
    Explanations

    emergency safety pool

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

    seeing results or actions

    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
     नाखूनों
    0.46
    栾
    0.42
    Mu
    0.42
     Pullman
    0.42
     Chop
    0.42
     Mussolini
    0.42
     সভা
    0.41
     creations
    0.41
    Victor
    0.41
    轳
    0.41
    POSITIVE LOGITS
     hyperglycemia
    0.54
     vigilant
    0.51
    꼼
    0.50
    ided
    0.49
    emergency
    0.48
    patient
    0.48
    緊急
    0.48
    efficient
    0.45
    counted
    0.45
    verm
    0.45
    Activations Density 0.004%

    No Known Activations