© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99819
    Prev
    Next
    INDEX
    Explanations

    attributions using by

    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_10/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
     
    -1.59
     этих
    -1.49
     mindestens
    -1.46
    '
    -1.46
    を探す
    -1.42
    三种
    -1.42
    すら
    -1.38
     paroisse
    -1.36
     katholischen
    -1.35
     conquête
    -1.35
    POSITIVE LOGITS
     our
    2.11
    hauled
    1.68
    
    1.64
     damen
    1.47
     gramos
    1.46
    𝐚
    1.45
    事的
    1.44
     黄色
    1.44
    𝒍
    1.42
     oku
    1.41
    Activations Density 0.032%

    No Known Activations