© 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. 16439
    Prev
    Next
    INDEX
    Explanations

    or it

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

    programming constructs

    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
    員の
    0.49
     circunferencia
    0.48
     dacă
    0.45
    🌦
    0.45
    輋
    0.45
    ぜひ
    0.44
     alternatif
    0.44
    ヘッド
    0.43
     kajian
    0.43
    𝘳
    0.43
    POSITIVE LOGITS
     Too
    0.53
    ator
    0.49
    anges
    0.49
    amma
    0.47
    lando
    0.47
    .
    0.46
    aks
    0.46
    apa
    0.45
    ello
    0.45
     Poor
    0.44
    Activations Density 0.000%

    No Known Activations