© 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. 115281
    Prev
    Next
    INDEX
    Explanations

    costs, then accounted for

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

    specific concepts and their associations

    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
     expresa
    0.48
    ืช
    0.47
     étn
    0.47
     různ
    0.46
     graphique
    0.46
     внутренней
    0.46
     cifras
    0.45
    乆
    0.45
     ioe
    0.45
     qnt
    0.44
    POSITIVE LOGITS
    ן
    0.53
    ley
    0.52
    ни
    0.51
    other
    0.48
    ens
    0.47
    clave
    0.47
    te
    0.46
    is
    0.46
    ल
    0.46
    ia
    0.45
    Activations Density 0.000%

    No Known Activations