© 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. 182765
    Prev
    Next
    INDEX
    Explanations

    beautiful pieces

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

    server, time, forecast, value, matrices

    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
    imenti
    0.55
     aspetto
    0.50
    ogli
    0.45
    のス
    0.45
     embark
    0.45
    했습니다
    0.44
    𝗂
    0.43
     wyróż
    0.43
    ahuan
    0.42
     gelişmeler
    0.42
    POSITIVE LOGITS
     tathapi
    0.43
     cryptographic
    0.42
     !(
    0.42
     detects
    0.40
    ട്ടില്‍
    0.40
     даже
    0.39
     pays
    0.39
     parses
    0.39
    ң
    0.39
     intolerant
    0.38
    Activations Density 0.001%

    No Known Activations