© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 191068
    Prev
    Next
    INDEX
    Explanations

    index=False

    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_40_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
     ізо
    0.42
    Nev
    0.41
    𠃊
    0.40
    ruptedException
    0.39
    Module
    0.39
    Diagn
    0.39
    Oro
    0.38
     predecessor
    0.37
    Flare
    0.37
     hẳn
    0.37
    POSITIVE LOGITS
    ellery
    0.40
     demokrasi
    0.38
     twins
    0.38
     harta
    0.38
     pram
    0.38
     সূত্রে
    0.37
     psychos
    0.37
    鯽
    0.37
     तालुका
    0.37
     recursos
    0.36
    Activations Density 0.001%

    No Known Activations