© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 53796
    Prev
    Next
    INDEX
    Explanations

    from __future__ import unicode_literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ویه
    -0.82
    Blo
    -0.74
     अभ
    -0.72
    decorators
    -0.71
    lette
    -0.71
    ASH
    -0.70
     Blooms
    -0.70
    ゲン
    -0.69
     Squares
    -0.67
     studying
    -0.67
    POSITIVE LOGITS
    lounge
    0.69
     eld
    0.69
     نه
    0.65
    ┣
    0.65
    ய
    0.65
     kee
    0.63
     PPM
    0.63
     sable
    0.62
     phenol
    0.62
     deserving
    0.61
    Activations Density 0.102%

    No Known Activations