Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11720
    Prev
    Next
    INDEX
    Explanations

    non-English and multi-script text

    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_22/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
     when
    -1.41
     from
    -1.33
    ؍
    -1.28
     battling
    -1.26
     it
    -1.24
     without
    -1.23
     establishing
    -1.22
     with
    -1.21
     and
    -1.20
     meticulously
    -1.20
    POSITIVE LOGITS
     REALLY
    1.53
     furia
    1.46
     AMAZING
    1.44
     enorme
    1.42
     durante
    1.37
     hugely
    1.36
     turmoil
    1.36
     .......
    1.35
     DURING
    1.35
    whose
    1.34
    Activations Density 0.024%

    No Known Activations