© 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. 44290
    Prev
    Next
    INDEX
    Explanations

    Elvis Presley

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

    "but I can"

    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
     प्लेइंग
    0.43
     bleiben
    0.42
    Fee
    0.41
    <unused60>
    0.40
    ender
    0.40
     FileName
    0.40
    вання
    0.40
    పో
    0.39
     soo
    0.39
     चतुर्थी
    0.39
    POSITIVE LOGITS
    萂
    0.48
    ழிப்பு
    0.41
     profess
    0.40
    ကျော်
    0.40
    issä
    0.39
    ítő
    0.39
     ممل
    0.39
    睒
    0.39
     Rimini
    0.39
     trailbl
    0.38
    Activations Density 0.000%

    No Known Activations