© 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. 34800
    Prev
    Next
    INDEX
    Explanations

    vote for, in development

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

    building SCADA applications

    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
    ологии
    0.43
    mical
    0.43
     둘
    0.43
    oko
    0.42
    근
    0.41
    ónio
    0.41
     potom
    0.41
     Monat
    0.41
    챌
    0.41
     symmet
    0.41
    POSITIVE LOGITS
     DAM
    0.51
    قابل
    0.49
    ScheduledAction
    0.48
     SAG
    0.46
     BALL
    0.45
     ENTRY
    0.45
     CAP
    0.44
    стів
    0.44
     CAM
    0.44
     DOWN
    0.44
    Activations Density 0.000%

    No Known Activations