© 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. 131555
    Prev
    Next
    INDEX
    Explanations

    locations or related contexts

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

    code comments, arrays, add

    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
     Màu
    0.51
    푦
    0.50
     Pengembangan
    0.49
     Concerto
    0.47
    PROCESSING
    0.45
    ☇
    0.45
     PSG
    0.45
    নির্
    0.45
    ▦
    0.44
    FromNib
    0.44
    POSITIVE LOGITS
    ции
    0.59
    uri
    0.51
    aren
    0.50
    '
    0.50
     uri
    0.49
    zen
    0.49
    ist
    0.48
    ende
    0.47
    थन
    0.46
     ignorance
    0.46
    Activations Density 0.000%

    No Known Activations