© 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. 3308
    Prev
    Next
    INDEX
    Explanations

    albatross and yes

    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
    Util
    0.50
    鐒
    0.50
    вую
    0.47
     Exit
    0.45
    Pdf
    0.45
    Discard
    0.44
    లకు
    0.44
    Hit
    0.43
    鸬
    0.43
    ᒧ
    0.43
    POSITIVE LOGITS
     inconn
    0.50
     competed
    0.47
     cinque
    0.45
     effet
    0.43
     cinq
    0.43
     información
    0.42
    tris
    0.42
    ern
    0.42
     iya
    0.41
     happened
    0.41
    Activations Density 0.008%

    No Known Activations