© 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. 2649
    Prev
    Next
    INDEX
    Explanations

    code functions definition

    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
     gave
    0.42
     ከአ
    0.39
     iterating
    0.39
    ہ
    0.39
     uncovering
    0.38
     signing
    0.38
     backing
    0.38
     ಅದೇ
    0.37
    ા
    0.37
     بجائے
    0.36
    POSITIVE LOGITS
    -
    0.47
    aken
    0.44
    ana
    0.42
     (!)
    0.42
    amerikan
    0.42
    _
    0.42
    sa
    0.41
    oping
    0.41
    ological
    0.41
    ORE
    0.41
    Activations Density 0.171%

    No Known Activations