© 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. 160817
    Prev
    Next
    INDEX
    Explanations

    percentage of, Journal of, knowledge of

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

    comparative evaluations and exceptions

    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
    }^{(
    0.43
     टू
    0.42
     harmonic
    0.41
    ⓐ
    0.41
    ⁤
    0.39
     kracht
    0.38
     Typ
    0.38
     monotonic
    0.38
    Traits
    0.38
    tFileInputExcel
    0.37
    POSITIVE LOGITS
     пат
    0.54
    signOut
    0.53
    ד
    0.52
     fizer
    0.49
    ariyam
    0.48
     Elovl
    0.48
    খাস্ত
    0.47
    ບໍ່
    0.47
    वत्ता
    0.46
     meny
    0.46
    Activations Density 0.000%

    No Known Activations