© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32651
    Prev
    Next
    INDEX
    Explanations

    gain access to exclusive content

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    聿
    -0.91
    大概是
    -0.88
     If
    -0.87
    してみて
    -0.86
    预约
    -0.86
     Because
    -0.85
     jeweiligen
    -0.85
     if
    -0.85
     tuttavia
    -0.85
    基本的
    -0.84
    POSITIVE LOGITS
     unlock
    1.17
     access
    1.10
    nicy
    1.04
    UNLOCK
    1.02
     член
    1.01
    unlock
    0.98
    зион
    0.98
    ъл
    0.97
    vium
    0.96
     pokrač
    0.96
    Activations Density 0.076%

    No Known Activations