© 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. 3825
    Prev
    Next
    INDEX
    Explanations

    selling points

    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
     solid
    0.40
     DBD
    0.37
     xmlns
    0.36
     亻
    0.36
     elicited
    0.36
     linéaire
    0.36
     ROS
    0.35
     linear
    0.35
    ⦁
    0.35
     oxalate
    0.35
    POSITIVE LOGITS
    <unused527>
    0.43
     bigotry
    0.40
    Obama
    0.39
     glauben
    0.39
    D
    0.39
    Ссы
    0.38
     Gesundheit
    0.38
    andaag
    0.37
    Dougall
    0.37
    lasse
    0.36
    Activations Density 0.002%

    No Known Activations