© 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. 104314
    Prev
    Next
    INDEX
    Explanations

    of before certain words

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

    Early experiments and village names

    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
     nœ
    0.46
     फॉर
    0.45
    endenza
    0.45
     व्हाउचर
    0.43
    欣赏
    0.43
    <unused82>
    0.43
    ాన్ని
    0.42
     लेती
    0.42
     Primera
    0.42
    ╿
    0.42
    POSITIVE LOGITS
    rots
    0.50
    ಜ
    0.47
    к
    0.46
    Qq
    0.46
     unaltered
    0.44
    ctrl
    0.44
    क्र
    0.43
    นาย
    0.43
    ("[%
    0.43
    all
    0.42
    Activations Density 0.000%

    No Known Activations