© 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. 81242
    Prev
    Next
    INDEX
    Explanations

    throw anything, demonstration team, config file

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

    instance, celebration, or API

    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
    齬
    0.53
    蛞
    0.52
    茈
    0.51
    搧
    0.48
    जव
    0.47
    kadang
    0.46
     veoma
    0.46
    激烈
    0.46
    ەد
    0.46
    这时
    0.46
    POSITIVE LOGITS
    т
    0.46
     offic
    0.45
     hires
    0.45
     كده
    0.44
     billi
    0.43
     cricketers
    0.43
    DialogOpen
    0.43
     supernovae
    0.43
    hires
    0.42
    onn
    0.42
    Activations Density 0.000%

    No Known Activations