© 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. 118844
    Prev
    Next
    INDEX
    Explanations

    file paths or directory names

    np_acts-logits-general · gemini-2.5-flash-lite

    file paths, particularly the forward slash characters that separate directory and file names in Unix-style paths.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     and
    -2.34
    1
    -1.58
     with
    -1.54
     also
    -1.53
     A
    -1.47
     has
    -1.45
     to
    -1.41
     same
    -1.39
    as
    -1.35
    更多
    -1.34
    POSITIVE LOGITS
    🦬
    1.60
    ambilan
    1.59
     cálido
    1.58
    ఙ
    1.58
    Mijn
    1.57
     expédié
    1.50
    鰨
    1.49
    उत्तर
    1.45
     desemple
    1.43
    puestas
    1.42
    Activations Density 0.074%

    No Known Activations