© 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. 193411
    Prev
    Next
    INDEX
    Explanations

    Museums and employee locations

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

    downloads multiple files

    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
    i
    0.56
    ي
    0.55
    On
    0.52
     will
    0.50
    й
    0.50
    م
    0.49
    ই
    0.48
     mistakenly
    0.47
    आ
    0.47
    ができ
    0.47
    POSITIVE LOGITS
     devad
    0.51
     muze
    0.50
     스테
    0.49
     arbeitete
    0.47
     razlik
    0.46
    otar
    0.46
    hattam
    0.46
    bitro
    0.46
     storyteller
    0.45
    рому
    0.44
    Activations Density 0.000%

    No Known Activations