© 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. 81177
    Prev
    Next
    INDEX
    Explanations

    agents, numbers, reputation, groups

    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
     (“
    0.44
     अपरा
    0.43
     margen
    0.41
     Бекер
    0.40
     evaluated
    0.40
     හැකිය
    0.40
     l
    0.39
    што
    0.39
    າ
    0.39
    วง
    0.39
    POSITIVE LOGITS
     WINDOW
    0.42
     Uint
    0.42
    ANIES
    0.41
     הת
    0.41
     aner
    0.41
     dipende
    0.41
    רים
    0.41
    ^{'
    0.41
    ೈನ್
    0.40
    ACK
    0.40
    Activations Density 0.000%

    No Known Activations