© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63114
    Prev
    Next
    INDEX
    Explanations

    code comments and licenses

    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
    нета
    -0.77
     volumen
    -0.76
     suis
    -0.68
    ớm
    -0.67
    ner
    -0.67
    Punkt
    -0.66
     cuida
    -0.65
    並
    -0.64
    ocino
    -0.64
    体系
    -0.63
    POSITIVE LOGITS
     ciphertext
    0.71
     culvert
    0.70
    တ်
    0.67
     Phar
    0.67
     transect
    0.66
    bacon
    0.66
    ří
    0.66
     Thule
    0.65
     obě
    0.64
    בוד
    0.63
    Activations Density 0.076%

    No Known Activations