© 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. 247521
    Prev
    Next
    INDEX
    Explanations

    programmewomenfitnessgiantssmall businesses

    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
     Акысыз
    0.47
     mathvariant
    0.47
     devoid
    0.46
    ocellular
    0.46
     straightforward
    0.46
     [,
    0.45
     hectare
    0.45
    w
    0.44
    異なる
    0.44
     taw
    0.44
    POSITIVE LOGITS
    ROLL
    0.47
    핑
    0.44
     imun
    0.44
    poline
    0.43
    了一些
    0.43
    imise
    0.43
    عد
    0.42
    াইয়া
    0.42
    IMA
    0.42
    İM
    0.41
    Activations Density 0.001%

    No Known Activations