© 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. 34-GEMMASCOPE-RES-131K
    7. 79279
    Prev
    Next
    INDEX
    Explanations

    in particular

    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
    大根
    -0.88
    ap
    -0.87
    om
    -0.86
    ́
    -0.84
     Angaben
    -0.83
    を持った
    -0.83
     zestawie
    -0.83
    cers
    -0.82
    さらに
    -0.81
    mining
    -0.79
    POSITIVE LOGITS
    ệp
    0.84
    řeb
    0.84
    ůž
    0.84
     gebou
    0.83
    ときは
    0.78
     beweging
    0.77
     inzwischen
    0.77
     CreateTagHelper
    0.76
    mischer
    0.76
     Objection
    0.75
    Activations Density 0.019%

    No Known Activations