© 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. 39457
    Prev
    Next
    INDEX
    Explanations

    applicable, apply, works

    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
    _
    -1.52
     graciosas
    -1.38
    стреча
    -1.35
     sufficient
    -1.35
     ample
    -1.34
     adequate
    -1.32
    шки
    -1.26
    izacin
    -1.24
     enough
    -1.22
    ⏤
    -1.22
    POSITIVE LOGITS
    1
    2.17
    2
    1.66
    4
    1.63
     peo
    1.52
    3
    1.47
     to
    1.38
    8
    1.36
     ceux
    1.34
     deaktiviert
    1.34
    p
    1.27
    Activations Density 0.084%

    No Known Activations