© 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. 54783
    Prev
    Next
    INDEX
    Explanations

    percentages, rules, and organizations

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

    Temporal artery

    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
    atiquement
    0.50
    Doors
    0.44
    ulkar
    0.43
     Remarkably
    0.43
    Collapse
    0.42
    }`).
    0.41
    kaan
    0.41
     Поэтому
    0.40
    uose
    0.40
     marqués
    0.40
    POSITIVE LOGITS
    ві
    0.58
    㑔
    0.53
     }},
    0.47
     prezzi
    0.46
    𝚎
    0.46
     c
    0.45
    чні
    0.45
     compra
    0.45
    督
    0.45
     ص
    0.44
    Activations Density 0.000%

    No Known Activations