© 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. 35149
    Prev
    Next
    INDEX
    Explanations

    more information or fewer

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

    founded or co-founded

    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
     pursue
    0.49
     Gry
    0.46
    nije
    0.45
    buyer
    0.43
    niji
    0.43
    zeugung
    0.43
    tsy
    0.42
    녓
    0.42
    purs
    0.42
    course
    0.42
    POSITIVE LOGITS
    訖
    0.45
    ErrorInfo
    0.43
     داده
    0.43
     spices
    0.42
     મદ
    0.42
     Parameter
    0.41
    ụng
    0.41
     stochastic
    0.40
     unim
    0.40
    \\
    0.40
    Activations Density 0.000%

    No Known Activations