© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90397
    Prev
    Next
    INDEX
    Explanations

    journal or log entries

    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
     patina
    0.48
    син
    0.46
    வைத்த
    0.44
     kontroll
    0.43
    囑
    0.42
    Marg
    0.42
     water
    0.41
     воду
    0.41
    Rein
    0.41
    頹
    0.41
    POSITIVE LOGITS
    lightbox
    0.42
    草原
    0.41
    <?
    0.38
     balancer
    0.38
     这
    0.38
     Tabelle
    0.38
     élargies
    0.38
     fenced
    0.38
     Tumblr
    0.38
    身份证
    0.38
    Activations Density 0.005%

    No Known Activations