© 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. 65229
    Prev
    Next
    INDEX
    Explanations

    wrap, surgery, reluctance

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

    French toast, Google Play, downhill, neurosurgeon

    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
    巖
    0.55
    ENERGY
    0.49
    礫
    0.48
    列車
    0.47
    玴
    0.47
    下跌
    0.47
    軺
    0.47
    存于
    0.47
    літ
    0.46
    顧客
    0.46
    POSITIVE LOGITS
     dicen
    0.47
     ler
    0.46
     डर
    0.45
     trainee
    0.45
     $\
    0.44
     BJP
    0.43
     tiene
    0.42
     iya
    0.42
     stepwise
    0.42
     tentative
    0.42
    Activations Density 0.000%

    No Known Activations