© 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. 47432
    Prev
    Next
    INDEX
    Explanations

    counting items

    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
    champ
    0.48
    cgi
    0.48
    opatra
    0.45
    }=\
    0.44
    joyed
    0.43
    膽
    0.43
    因為
    0.43
    zilla
    0.43
    }{-
    0.42
    =(\
    0.42
    POSITIVE LOGITS
    لت
    0.47
     handcrafted
    0.47
     trow
    0.44
     percepción
    0.44
     docks
    0.43
    لین
    0.43
     extens
    0.42
     इसे
    0.42
     lanz
    0.42
     adhes
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.