© 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. 100931
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    lifestyle changes

    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
    ے
    0.46
    טי
    0.44
    Didn
    0.44
     Didn
    0.42
     distributional
    0.41
    اج
    0.40
    ی
    0.40
    dS
    0.40
     LIB
    0.39
     "")
    0.39
    POSITIVE LOGITS
    érc
    0.55
    anie
    0.54
    ła
    0.52
     уважаемые
    0.52
    án
    0.51
    álně
    0.51
    ció
    0.50
    ilization
    0.50
    ología
    0.50
    aceous
    0.50
    Activations Density 0.003%

    No Known Activations