© 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. 44119
    Prev
    Next
    INDEX
    Explanations

    actions by instructions

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

    teaching a dog

    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
     misery
    0.49
    ിലേക്ക്
    0.44
     foiled
    0.44
    ளை
    0.43
     sizzling
    0.41
    {},
    0.41
     allergies
    0.41
    สำหรับ
    0.40
    َي
    0.40
     zwei
    0.40
    POSITIVE LOGITS
     регу
    0.45
    াহিয়া
    0.44
    Regulatory
    0.43
    Drag
    0.43
    Kenn
    0.43
    Assemblies
    0.43
    Propagation
    0.42
    Gosudarstvennyj
    0.42
     പക്ഷേ
    0.41
    мих
    0.40
    Activations Density 0.000%

    No Known Activations