© 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. 7076
    Prev
    Next
    INDEX
    Explanations

    identifying official context method deviations

    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
    but
    0.36
     B
    0.35
     Rostov
    0.34
    b
    0.34
     Bari
    0.33
    Roth
    0.33
     Wirtschaft
    0.33
     Marian
    0.32
     sitcom
    0.32
     Alsace
    0.32
    POSITIVE LOGITS
    袒
    0.35
     inducement
    0.34
    르
    0.34
     の
    0.33
     embarrassment
    0.32
     milligrams
    0.31
     annoyance
    0.31
     そんな
    0.31
     hydration
    0.31
    ргә
    0.31
    Activations Density 1.134%

    No Known Activations