© 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. 24289
    Prev
    Next
    INDEX
    Explanations

    infinitive, perfectly, scope, impediment

    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
    ડિયા
    0.52
    ែក
    0.48
    船
    0.48
    環境
    0.47
    わ
    0.46
    दय
    0.46
    ុក
    0.45
    ន្ថ
    0.45
    asiun
    0.45
    수
    0.45
    POSITIVE LOGITS
     Biographical
    0.44
     legg
    0.42
     இருக்கும்
    0.40
     Proverbs
    0.40
     जोर
    0.40
     proverb
    0.39
     leg
    0.39
     Minder
    0.39
    spr
    0.39
     Keeping
    0.39
    Activations Density 0.002%

    No Known Activations