© 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. 79090
    Prev
    Next
    INDEX
    Explanations

    balance of features

    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
     सफ़ेद
    0.51
    <unused532>
    0.50
    odils
    0.50
     ---------------
    0.48
     Uran
    0.48
    룺
    0.48
     بەر
    0.48
    엥
    0.48
    <unused477>
    0.48
     எதிர்க
    0.48
    POSITIVE LOGITS
    ).
    0.49
     cust
    0.42
     custodia
    0.41
     protección
    0.41
    '.
    0.40
    cciones
    0.39
     class
    0.38
     glass
    0.37
     mild
    0.37
     अच्छा
    0.37
    Activations Density 0.002%

    No Known Activations