© 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. 80488
    Prev
    Next
    INDEX
    Explanations

    liabilities, project, heat, ice

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

    common topics and subjects

    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
    ığınız
    0.52
     artific
    0.47
     eléct
    0.46
     ஆர்
    0.45
     وار
    0.45
    oches
    0.45
    setUrl
    0.45
     宋
    0.44
     பு
    0.44
    🐏
    0.44
    POSITIVE LOGITS
    預
    0.47
    hepat
    0.46
     preposition
    0.45
     embry
    0.43
     molecule
    0.43
     institution
    0.43
     grammar
    0.42
     papill
    0.42
     krok
    0.41
     mycop
    0.41
    Activations Density 0.000%

    No Known Activations