© 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. 143457
    Prev
    Next
    INDEX
    Explanations

    international treaties; top starts and finishes

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

    solving equations by substitution

    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
     Andri
    0.49
    ंधी
    0.49
     Ad
    0.45
     Change
    0.44
     싸
    0.44
     Cambio
    0.44
     تغير
    0.43
     သူ့
    0.43
    ง่าย
    0.43
     swear
    0.42
    POSITIVE LOGITS
     `'\\
    0.48
    vinced
    0.48
    的基础
    0.47
    の発
    0.46
    穗
    0.45
     majeur
    0.45
     `'
    0.44
    十二
    0.44
    匏
    0.44
     `>`,
    0.44
    Activations Density 0.000%

    No Known Activations