© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 22870
    Prev
    Next
    INDEX
    Explanations

    depend on, need to, cannot

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

    lists, math, or code

    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
    leftrightarrow
    0.43
    disease
    0.42
     Kipp
    0.42
     hats
    0.41
     Suits
    0.41
     Anleitung
    0.41
    dom
    0.41
     `
    0.40
    back
    0.40
     Seb
    0.40
    POSITIVE LOGITS
    まず
    0.47
    VIDENCE
    0.46
    ड्रा
    0.46
     trám
    0.45
     vâr
    0.45
     પ્રથમ
    0.43
     सर्वप्रथम
    0.43
    aap
    0.42
    實
    0.42
    क़
    0.42
    Activations Density 0.000%

    No Known Activations