© 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. 73547
    Prev
    Next
    INDEX
    Explanations

    html href attributes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    }
    -1.71
     
    -1.59
    その
    -1.57
    これを
    -1.46
    をも
    -1.45
    These
    -1.40
     It
    -1.39
     carry
    -1.37
     offer
    -1.34
    この
    -1.31
    POSITIVE LOGITS
     and
    1.59
     hermosos
    1.56
     człowie
    1.53
    蟊
    1.49
    ‪.‬‬
    1.47
    ⬚
    1.42
    ᯅ
    1.39
     hijau
    1.39
    猡
    1.36
     mereka
    1.30
    Activations Density 0.003%

    No Known Activations