© 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. 59978
    Prev
    Next
    INDEX
    Explanations

    appointed or elected

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

    redefine

    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
     Moreton
    0.45
    રોના
    0.44
    烜
    0.43
    μέ
    0.43
    NAMES
    0.43
     vált
    0.43
     moelle
    0.43
     श्रीवास्तव
    0.42
     مزید
    0.42
    ÉRI
    0.42
    POSITIVE LOGITS
    acom
    0.38
     applicant
    0.35
     idealism
    0.35
    ato
    0.35
    已知
    0.35
    true
    0.34
     ஆக
    0.34
    析
    0.34
    ist
    0.34
     comprehension
    0.34
    Activations Density 0.000%

    No Known Activations