© 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. 134311
    Prev
    Next
    INDEX
    Explanations

    painted, lost daughter, enables Joliet

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

    like this, immunity threshold

    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
     imper
    0.44
    jung
    0.41
    ङ
    0.40
     anses
    0.40
     james
    0.39
    upiter
    0.39
     ha
    0.39
    uhl
    0.39
    ണ്ഡ
    0.39
    🔝
    0.38
    POSITIVE LOGITS
    燦
    0.48
     phù
    0.46
     કાર્યવાહી
    0.45
    ΤΟ
    0.44
     Acrylic
    0.43
     IDENT
    0.43
     драма
    0.43
    classmethod
    0.42
     पद्धतीने
    0.42
     সন
    0.42
    Activations Density 0.000%

    No Known Activations