© 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. 234307
    Prev
    Next
    INDEX
    Explanations

    administration, concluded, development, plugs, loosen

    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
     Тео
    0.49
     Emperor
    0.49
     Сте
    0.46
     امن
    0.46
     Psi
    0.44
     Ο
    0.44
     Пара
    0.44
     Константи
    0.44
     emperor
    0.43
     Świę
    0.43
    POSITIVE LOGITS
    쏨
    0.53
    AssignableFrom
    0.52
    재
    0.51
    HM
    0.50
     solicitation
    0.49
    촐
    0.49
     hasten
    0.48
     solicit
    0.47
    ivité
    0.46
    은
    0.46
    Activations Density 0.002%

    No Known Activations