© 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. 2670
    Prev
    Next
    INDEX
    Explanations

    0-60 mph and car speeds

    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
     sunday
    0.41
    t
    0.40
     bit
    0.40
     Sides
    0.40
     Monday
    0.40
    ↵
    0.39
     shen
    0.39
    ombie
    0.39
     monday
    0.39
     \]
    0.39
    POSITIVE LOGITS
    셉
    0.44
     accusation
    0.43
    িন্দ
    0.43
     confiance
    0.43
    ინგ
    0.43
     історії
    0.42
     accusations
    0.42
     warum
    0.41
    🥱
    0.41
    ক্ষণের
    0.41
    Activations Density 0.014%

    No Known Activations