© 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. 47973
    Prev
    Next
    INDEX
    Explanations

    interconnect and complex relationships

    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
    ९
    0.45
    га
    0.44
    }}
    0.43
    dekat
    0.42
    ិ
    0.41
    د
    0.40
    ৯
    0.40
    क
    0.39
    ۷
    0.39
     영
    0.39
    POSITIVE LOGITS
     dialogo
    0.43
     rispetto
    0.42
     caro
    0.42
     بیاکت
    0.41
     charges
    0.41
     bords
    0.41
     poté
    0.41
     répar
    0.41
    抬
    0.41
     stora
    0.40
    Activations Density 0.005%

    No Known Activations