© 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. 75841
    Prev
    Next
    INDEX
    Explanations

    person / title / name

    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
     it
    -1.59
     you
    -1.37
    corrhi
    -1.28
    際に
    -1.24
    になったら
    -1.21
    際は
    -1.20
    際の
    -1.20
     zelve
    -1.19
    際には
    -1.16
    nexpected
    -1.15
    POSITIVE LOGITS
     a
    2.44
     the
    1.55
    the
    1.42
     some
    1.29
     an
    1.17
    randrange
    1.16
     everything
    1.16
    一套
    1.14
    this
    1.13
    some
    1.13
    Activations Density 0.063%

    No Known Activations