© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 10302
    Prev
    Next
    INDEX
    Explanations

    tutorials documentation guides resources

    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
    ↵
    0.55
    ↵↵
    0.52
    اد
    0.40
    '
    0.39
    ation
    0.39
     Motivation
    0.38
    ↵↵↵
    0.38
    </s>
    0.38
    .
    0.38
    ingly
    0.37
    POSITIVE LOGITS
     olds
    0.55
     scarring
    0.50
    ಬ
    0.48
     cicat
    0.48
     overwritten
    0.48
     rumoured
    0.47
    轵
    0.47
     trampled
    0.46
     ಬ
    0.45
     rumours
    0.45
    Activations Density 0.001%

    No Known Activations