© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 242536
    Prev
    Next
    INDEX
    Explanations

    village location list

    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
     massaging
    0.52
    \
    0.48
     fluttering
    0.48
     +
    0.46
     odorless
    0.45
     emot
    0.44
    -
    0.44
    '-
    0.44
     exhilar
    0.44
     tug
    0.44
    POSITIVE LOGITS
    MULT
    0.58
    Marker
    0.56
    LEFT
    0.56
    Annot
    0.55
    CACHE
    0.55
    Meier
    0.55
    TaskList
    0.55
    Naive
    0.54
    Logical
    0.53
    MinWidth
    0.52
    Activations Density 0.001%

    No Known Activations