© 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. 59632
    Prev
    Next
    INDEX
    Explanations

    final editscopy and documentationfestive occasionsreturn policies

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

    handles all the servers

    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
    Algun
    0.56
    轉換
    0.52
    éristiques
    0.52
    Sí
    0.52
     أنه
    0.50
    貸款
    0.50
     órdenes
    0.49
    軀
    0.49
    Nueva
    0.49
    ්ර
    0.49
    POSITIVE LOGITS
    oot
    0.47
     Mout
    0.47
     demokrasi
    0.47
    nol
    0.47
     wigs
    0.46
     gossip
    0.45
     كذلك
    0.44
     slog
    0.43
     nemat
    0.43
     sop
    0.43
    Activations Density 0.001%

    No Known Activations