© 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. 168765
    Prev
    Next
    INDEX
    Explanations

    approved deadline % written cause prints

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

    absurdism

    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
    quel
    0.42
    ancel
    0.41
     Prevalence
    0.41
     মিলিয়ন
    0.40
    embedded
    0.40
    되었
    0.40
    摩
    0.39
    pret
    0.39
     الام
    0.39
    <0x91>
    0.39
    POSITIVE LOGITS
    COPY
    0.58
    HALF
    0.54
     layi
    0.52
     FILL
    0.51
    र्टी
    0.50
     gleiche
    0.49
     hepinize
    0.49
    VISED
    0.49
    BLUE
    0.49
     ihe
    0.49
    Activations Density 0.000%

    No Known Activations