© 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. 158594
    Prev
    Next
    INDEX
    Explanations

    interior doors

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

    personal feelings and descriptions

    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
    錤
    0.47
    മിഷ
    0.46
    ऑक्साइड
    0.46
     Patio
    0.46
     Oasis
    0.45
    ohia
    0.44
     Puoi
    0.44
    decks
    0.43
     überras
    0.43
    পুল
    0.43
    POSITIVE LOGITS
    ami
    0.47
    ý
    0.46
    eri
    0.44
     papier
    0.43
    anish
    0.43
     общественного
    0.41
    の関係
    0.41
    ě
    0.40
    kö
    0.40
     Andal
    0.40
    Activations Density 0.000%

    No Known Activations