© 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. 27405
    Prev
    Next
    INDEX
    Explanations

    books or information about banks

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

    lists of items

    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
    bagai
    0.39
    ádiz
    0.39
    ופ
    0.39
    󠁴
    0.38
    르
    0.37
     TRANSPORTURI
    0.37
    ੍ਰ
    0.37
    ნი
    0.36
    టువంటి
    0.36
    до
    0.36
    POSITIVE LOGITS
     B
    0.36
     Data
    0.34
     MSS
    0.34
     Ch
    0.33
     SVM
    0.33
     Patents
    0.32
     SSM
    0.31
     S
    0.31
     Library
    0.31
     Iowa
    0.30
    Activations Density 0.042%

    No Known Activations