© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90349
    Prev
    Next
    INDEX
    Explanations

    Integral polytope, Combinations, unanswered

    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
     этой
    -1.56
     their
    -1.41
     like
    -1.41
    ׄ
    -1.40
     I
    -1.38
     और
    -1.38
     this
    -1.35
    ֺ
    -1.32
     my
    -1.31
     sicht
    -1.30
    POSITIVE LOGITS
    ּוֹ
    1.59
     אַ
    1.59
     but
    1.56
     quelconque
    1.53
    ditionally
    1.46
     produrre
    1.46
    maktadır
    1.45
     supuestamente
    1.43
    StateToProps
    1.42
     Hydrology
    1.41
    Activations Density 0.000%

    No Known Activations