© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20697
    Prev
    Next
    INDEX
    Explanations

    headings, rain, Gen Z, AAVE, civil servants, domains, securities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    вили
    0.45
     Віль
    0.45
    dsc
    0.45
    жными
    0.44
    ikesh
    0.44
    lov
    0.44
     Unlike
    0.43
    ¹.
    0.43
    pil
    0.42
    сля
    0.42
    POSITIVE LOGITS
     despre
    0.50
     punto
    0.50
     terza
    0.49
     underpinning
    0.48
     ergän
    0.47
     aument
    0.47
    娛樂
    0.47
     ultimo
    0.46
     fireball
    0.46
     robi
    0.45
    Activations Density 0.002%

    No Known Activations