© 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. 210620
    Prev
    Next
    INDEX
    Explanations

    services and information

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

    aid and support

    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
     Butte
    0.45
    挤
    0.45
    预计
    0.44
     Thrift
    0.44
    行驶
    0.44
    大量的
    0.42
    一个个
    0.42
    த்தனர்
    0.42
    雉
    0.41
    轲
    0.41
    POSITIVE LOGITS
     comforting
    0.54
     saluto
    0.48
     کمک
    0.46
     unterstützen
    0.46
     sponsoring
    0.46
     bleiben
    0.46
     mentorship
    0.45
     lingk
    0.45
     apoyo
    0.45
     policym
    0.45
    Activations Density 0.002%

    No Known Activations