© 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. 31-GEMMASCOPE-2-RES-65K
    7. 36047
    Prev
    Next
    INDEX
    Explanations

    What would it take

    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_65k_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
    *)&
    0.45
    බන්ධ
    0.44
    ణాలు
    0.41
     aram
    0.41
     membaca
    0.41
     hablar
    0.40
    ධා
    0.40
     visit
    0.40
     habla
    0.40
    लों
    0.40
    POSITIVE LOGITS
     WHICH
    0.49
    zaXRvcn
    0.47
    なり
    0.45
    Aless
    0.43
    감
    0.43
    τροπ
    0.42
     мето
    0.42
    ειο
    0.42
     הח
    0.42
     estet
    0.42
    Activations Density 0.012%

    No Known Activations