© 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. 121625
    Prev
    Next
    INDEX
    Explanations

    plan regarding

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

    social progress

    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
    ل
    0.55
    ला
    0.53
     Mandal
    0.51
    la
    0.51
    T
    0.48
    dır
    0.47
     Tongue
    0.47
    lide
    0.46
     Bilal
    0.46
     الداخلية
    0.46
    POSITIVE LOGITS
    ួល
    0.48
    」，
    0.46
     erreur
    0.46
     Gesellschaft
    0.45
    Parameter
    0.43
    װ
    0.43
     DEFAULT
    0.43
     парамет
    0.43
     kesalahan
    0.42
     weißen
    0.42
    Activations Density 0.001%

    No Known Activations