© 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-262K
    7. 24020
    Prev
    Next
    INDEX
    Explanations

    recent past events

    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
    <sup>
    0.46
     dew
    0.45
     scarcely
    0.45
    <sub>
    0.44
     more
    0.41
    ↵↵
    0.41
     badi
    0.41
    à
    0.41
     his
    0.40
     homozygous
    0.40
    POSITIVE LOGITS
     گزشتہ
    0.53
     vergang
    0.52
     afgelopen
    0.47
    潋
    0.46
    지난
    0.45
    昨
    0.45
    녠
    0.45
     সহিংস
    0.45
     récente
    0.45
     scorsa
    0.43
    Activations Density 0.003%

    No Known Activations