© 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. 73127
    Prev
    Next
    INDEX
    Explanations

    KELL's, CLUS's

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

    bullet points and bold text

    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
     relatable
    0.42
    XA
    0.42
     D
    0.40
     Sh
    0.38
     Dong
    0.38
    dong
    0.38
     Retrieved
    0.38
    otyp
    0.37
     Dat
    0.37
     dong
    0.37
    POSITIVE LOGITS
     clockRadius
    0.42
     wur
    0.40
    getPosition
    0.39
     мыш
    0.38
     كثير
    0.38
     envolve
    0.38
    íonn
    0.38
    áš
    0.37
    曏
    0.37
     시간에는
    0.37
    Activations Density 0.009%

    No Known Activations