© 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. 34-GEMMASCOPE-RES-131K
    7. 78993
    Prev
    Next
    INDEX
    Explanations

    speed and competition

    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
    wtf
    -0.83
     semacam
    -0.81
    オブ
    -0.81
     probablemente
    -0.78
    ค่ะ
    -0.77
    ълга
    -0.77
    分区
    -0.75
    thaf
    -0.75
    filme
    -0.75
     resus
    -0.75
    POSITIVE LOGITS
     morceaux
    0.90
     fastest
    0.87
     tỏ
    0.84
     HUNT
    0.83
    endl
    0.82
    ваться
    0.82
    子和
    0.81
     spree
    0.81
    しっかりと
    0.79
    禍
    0.78
    Activations Density 0.025%

    No Known Activations