© 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-65K
    7. 45240
    Prev
    Next
    INDEX
    Explanations

    objectives and impact

    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_65k_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
    or
    0.47
    his
    0.44
     मिश
    0.43
     महीने
    0.43
    Ongoing
    0.42
    their
    0.42
    o
    0.42
    other
    0.41
    如今
    0.41
    ispiels
    0.41
    POSITIVE LOGITS
    ষধ
    0.54
     eukaryotes
    0.49
     legjob
    0.47
     ∀
    0.47
     ignite
    0.47
     inferences
    0.47
     endem
    0.46
     analyte
    0.46
     idiots
    0.46
     extrem
    0.46
    Activations Density 0.044%

    No Known Activations