© 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. 46825
    Prev
    Next
    INDEX
    Explanations

    Agency MBS, seasonal, pointer, denomination, System Album

    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
    ﾘ
    0.44
    <unused338>
    0.43
     всем
    0.41
     утвер
    0.41
     같
    0.40
     רק
    0.40
     божомолу
    0.40
     үшін
    0.40
     indicó
    0.40
     песен
    0.39
    POSITIVE LOGITS
     access
    0.45
     utilizzare
    0.42
     near
    0.40
     Super
    0.39
     dislocations
    0.39
     blood
    0.39
     ingenious
    0.38
    aided
    0.38
     "
    0.38
     covered
    0.38
    Activations Density 0.008%

    No Known Activations