© 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. 30622
    Prev
    Next
    INDEX
    Explanations

    knows senior care

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

    code/technical instruction

    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
    OTS
    0.42
     F
    0.39
    8
    0.38
    onym
    0.38
    OP
    0.38
     weird
    0.37
     Duration
    0.37
     Positive
    0.37
    台
    0.37
     tik
    0.37
    POSITIVE LOGITS
    recognizable
    0.48
    expansive
    0.47
     loosening
    0.46
     expansive
    0.45
    elben
    0.45
     প্রজাতির
    0.45
     trasporto
    0.45
     транспорти
    0.44
     เนื่องจาก
    0.44
     راہ
    0.44
    Activations Density 0.000%

    No Known Activations