© 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. 69782
    Prev
    Next
    INDEX
    Explanations

    override method declarations

    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
     потрібно
    -1.40
    ,,,,
    -1.31
    釭
    -1.30
     fathoms
    -1.29
    inside
    -1.25
     intestines
    -1.23
     ideologies
    -1.23
     genitals
    -1.23
    ouille
    -1.23
     divertida
    -1.21
    POSITIVE LOGITS
    The
    1.88
    鄚
    1.60
     such
    1.43
     nahil
    1.41
     that
    1.39
     they
    1.38
    ﮑ
    1.38
     uovo
    1.34
     '>=
    1.34
     llor
    1.34
    Activations Density 0.006%

    No Known Activations