© 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. 97092
    Prev
    Next
    INDEX
    Explanations

    state or limit

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

    symbol or CUSIP

    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
    B
    0.61
    Q
    0.56
    D
    0.54
    W
    0.54
    L
    0.52
    T
    0.51
    P
    0.49
    M
    0.49
    f
    0.48
    la
    0.48
    POSITIVE LOGITS
     Alguns
    0.54
     Ă
    0.53
     scritt
    0.52
     messageShow
    0.52
     SrvGroup
    0.51
     клет
    0.51
     Ronde
    0.50
     సి
    0.50
     少し
    0.50
    㳻
    0.49
    Activations Density 0.002%

    No Known Activations