© 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. 173325
    Prev
    Next
    INDEX
    Explanations

    "check before"

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

    instructions, directions, or pathways

    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
    গ্রাফ
    0.47
    fun
    0.46
     rupee
    0.45
     ሽፋ
    0.44
    '])[
    0.44
     francs
    0.43
    রাষ্ট্রে
    0.43
    unable
    0.42
     নিলাম
    0.41
    onnage
    0.41
    POSITIVE LOGITS
     Yol
    0.49
     настоя
    0.49
    ㅕ
    0.48
    ត្រ
    0.47
     Esper
    0.47
     Vite
    0.47
    서
    0.47
     Jog
    0.47
    精华
    0.46
     Yok
    0.45
    Activations Density 0.001%

    No Known Activations