© 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. 73561
    Prev
    Next
    INDEX
    Explanations

    saving time and resources

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

    absolutely, yes

    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
     grossly
    0.54
     captioned
    0.50
     gemäß
    0.48
     adaptés
    0.46
     적
    0.44
     tokom
    0.44
     جري
    0.44
     cadet
    0.44
     fearful
    0.43
     debating
    0.43
    POSITIVE LOGITS
    t
    0.66
    G
    0.48
    रु
    0.47
    Aurora
    0.47
    \,\
    0.46
    tumor
    0.46
    F
    0.46
    TL
    0.46
    nature
    0.46
    نما
    0.46
    Activations Density 0.001%

    No Known Activations