© 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. 7031
    Prev
    Next
    INDEX
    Explanations

    cash, determined, marginal patterns

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

    list concatenation, code, Japanese

    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
     Nasıl
    0.51
     Autres
    0.48
     这里
    0.47
    ٣
    0.47
     importância
    0.47
     করিতাম
    0.47
     FILM
    0.46
     SimSun
    0.45
     MET
    0.45
    NASDAQ
    0.45
    POSITIVE LOGITS
    lab
    0.57
    mysqli
    0.49
    t
    0.49
    人數
    0.48
    subsec
    0.46
    rase
    0.46
    li
    0.45
    lld
    0.45
    Developed
    0.45
    lans
    0.45
    Activations Density 0.000%

    No Known Activations