© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45348
    Prev
    Next
    INDEX
    Explanations

    claims expansion

    np_acts-logits-general · gemini-2.5-flash-lite

    sentiment analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aktionen
    0.58
    पों
    0.54
     sebagaimana
    0.53
    ありがとうございました
    0.52
     incluida
    0.52
     sehingga
    0.51
    ᥒ
    0.50
     selanjutnya
    0.50
    𝐣
    0.50
     meliputi
    0.50
    POSITIVE LOGITS
    0.49
     Osbourne
    0.42
     alternatives
    0.42
     oscillations
    0.41
     dampers
    0.41
     branded
    0.40
    down
    0.40
    Level
    0.40
    Culture
    0.39
    Master
    0.39
    Activations Density 0.000%

    No Known Activations