© 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. 155569
    Prev
    Next
    INDEX
    Explanations

    habitual patterns

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

    generic, Mariana, llama, tips, ipv

    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
     (\
    0.54
    おり
    0.50
     interchanges
    0.49
     $-\
    0.48
    texttt
    0.47
     subclasses
    0.46
     $-
    0.46
    (\|\
    0.45
    的三
    0.43
    transfected
    0.43
    POSITIVE LOGITS
     Jawah
    0.44
     guy
    0.43
     name
    0.43
     convent
    0.43
     hardworking
    0.43
    령
    0.43
    渺
    0.43
     Jehova
    0.43
    FONT
    0.42
     Akk
    0.42
    Activations Density 0.000%

    No Known Activations