© 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. 2182
    Prev
    Next
    INDEX
    Explanations

    explaining sections

    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
     handleSubmit
    0.39
    í
    0.39
    思考
    0.39
     Echo
    0.38
    身后
    0.38
    を果た
    0.37
    也就是说
    0.37
    onto
    0.36
     Jonah
    0.36
    韧
    0.36
    POSITIVE LOGITS
     aspart
    0.45
     plazas
    0.45
     assembl
    0.44
    <0x00>
    0.42
    BED
    0.42
    CYCL
    0.42
    EMP
    0.42
    METAL
    0.42
     rufo
    0.41
     gols
    0.41
    Activations Density 0.132%

    No Known Activations