© 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. 241852
    Prev
    Next
    INDEX
    Explanations

    word followed by specific word/punctuation

    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
    autes
    0.44
    hia
    0.43
     glycerol
    0.43
     vultures
    0.42
    ariums
    0.42
     reps
    0.42
     個
    0.41
    ou
    0.41
     السماء
    0.41
     gangs
    0.40
    POSITIVE LOGITS
    Moon
    0.51
    ඓ
    0.49
    Breaking
    0.48
     nàng
    0.47
    İstanbul
    0.47
    Physics
    0.46
    ᒃ
    0.46
     previsão
    0.46
    ணன்
    0.45
    Aston
    0.45
    Activations Density 0.001%

    No Known Activations