© 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. 23714
    Prev
    Next
    INDEX
    Explanations

    specific data points

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

    tables listing features

    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
     &/
    0.40
     resident
    0.39
     partnered
    0.39
     تنفيذ
    0.39
     Resident
    0.37
     mów
    0.37
    ッと
    0.36
     Trên
    0.36
     Gorgeous
    0.36
     మొద
    0.35
    POSITIVE LOGITS
    ᅣ
    0.44
    ൭
    0.42
    ⵚ
    0.42
    ᡧ
    0.42
    рс
    0.41
    䫝
    0.41
    zame
    0.40
    ဆံ
    0.40
    ํ
    0.40
    ュー
    0.40
    Activations Density 0.001%

    No Known Activations