© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4595
    Prev
    Next
    INDEX
    Explanations

    Expiration Date

    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_16k_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
    inv
    0.50
    as
    0.47
    ZE
    0.47
    ’
    0.45
    ला
    0.45
    不算
    0.43
    olla
    0.42
    सभी
    0.42
    ש
    0.42
    സ്
    0.42
    POSITIVE LOGITS
    曌
    0.53
     fain
    0.49
     ምልክ
    0.49
    ካት
    0.48
     Corinthians
    0.47
     quarrel
    0.47
     rencontres
    0.47
     stereotype
    0.46
     Austr
    0.46
    橥
    0.46
    Activations Density 0.078%

    No Known Activations