© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101293
    Prev
    Next
    INDEX
    Explanations

    creamy, crunchy, velvety, chunky

    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
    '')
    -2.23
    ￬
    -2.17
    最
    -2.16
    selben
    -2.13
    
    -2.13
    medriver
    -2.06
     katkıda
    -2.06
    seitige
    -2.06
    蟜
    -2.05
    ſtre
    -2.00
    POSITIVE LOGITS
    -
    2.28
     мы
    2.28
     poignant
    2.17
     unquestionably
    2.13
    _
    2.08
     sehr
    2.05
     rebellious
    1.93
     illustrates
    1.91
    .<
    1.89
    <
    1.89
    Activations Density 0.002%

    No Known Activations