© 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. 42903
    Prev
    Next
    INDEX
    Explanations

    searching code

    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
    al
    -2.52
    на
    -2.45
     mais
    -2.27
    だが
    -2.23
     to
    -2.16
    er
    -2.13
     Until
    -2.09
     широкий
    -2.06
    us
    -2.06
    en
    -2.00
    POSITIVE LOGITS
    寕
    2.84
    䛗
    2.41
     好看
    2.39
    嵛
    2.36
     jesús
    2.31
    耵
    2.27
     gustado
    2.27
     olvidado
    2.25
     漂亮
    2.23
     pauv
    2.22
    Activations Density 0.004%

    No Known Activations