© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28382
    Prev
    Next
    INDEX
    Explanations

    file paths and unicode characters

    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
     and
    -3.11
     as
    -2.11
     or
    -1.73
     for
    -1.58
     with
    -1.53
     will
    -1.50
     With
    -1.49
     before
    -1.45
     within
    -1.41
     one
    -1.38
    POSITIVE LOGITS
     Grüßen
    1.71
    もある
    1.66
     Inſ
    1.66
    もあって
    1.66
     configurações
    1.65
     blatant
    1.62
     MATTERS
    1.62
     deliciously
    1.61
     MAKES
    1.61
     delightfully
    1.58
    Activations Density 0.021%

    No Known Activations