© 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. 71306
    Prev
    Next
    INDEX
    Explanations

    нужно / need / is necessary

    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
    the
    -3.00
    2
    -2.92
    ar
    -2.92
    ol
    -2.88
    的
    -2.80
    ኧ
    -2.67
            
    -2.58
    sh
    -2.55
    o
    -2.53
    my
    -2.47
    POSITIVE LOGITS
    逦
    2.61
    縯
    2.50
    鸶
    2.45
    felpa
    2.42
     constitución
    2.42
    vantaged
    2.31
     brushing
    2.30
    gyz
    2.20
    骈
    2.20
     concepción
    2.19
    Activations Density 0.004%

    No Known Activations