© 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. 34-GEMMASCOPE-RES-131K
    7. 76347
    Prev
    Next
    INDEX
    Explanations

    definition and assignment

    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
     wiedzieć
    -1.41
     menek
    -1.35
     Europese
    -1.34
    鶿
    -1.26
     elefante
    -1.22
     dévou
    -1.21
     mû
    -1.20
     kupić
    -1.20
    鳢
    -1.18
    ところです
    -1.16
    POSITIVE LOGITS
     with
    1.42
     in
    1.38
     throw
    1.34
     when
    1.26
     but
    1.25
     since
    1.17
     without
    1.16
    はお
    1.14
    throw
    1.13
     thrown
    1.13
    Activations Density 0.007%

    No Known Activations