© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33560
    Prev
    Next
    INDEX
    Explanations

    has has have have to

    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
    してみてください
    -1.40
     has
    -1.25
     have
    -1.23
     be
    -1.17
     was
    -1.16
    これは
    -1.13
     departament
    -1.02
    r
    -1.02
    ประเทศ
    -1.01
    iennes
    -0.99
    POSITIVE LOGITS
     to
    2.09
     a
    1.66
    明日は
    1.53
     enough
    1.42
    ビックリ
    1.38
     generan
    1.38
     cancelamento
    1.37
     desejo
    1.32
    が一番
    1.32
    為に
    1.31
    Activations Density 0.092%

    No Known Activations