© 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. 12727
    Prev
    Next
    INDEX
    Explanations

    expressions of laughter

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

    positive emojis

    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
    糟
    0.38
    ቈ
    0.37
    باب
    0.35
     জনসাধারণের
    0.35
    훨
    0.35
    !...
    0.34
    ,..
    0.34
    ...!
    0.33
    𝐼
    0.33
     Engines
    0.33
    POSITIVE LOGITS
     meeste
    0.38
     беше
    0.36
    usern
    0.36
     強
    0.35
    unity
    0.35
     इसने
    0.34
    🤣
    0.33
    enh
    0.33
    substrate
    0.33
     其实
    0.33
    Activations Density 0.014%

    No Known Activations