© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26966
    Prev
    Next
    INDEX
    Explanations

    identifying someone by relation

    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
    yship
    -1.41
    tifiable
    -1.21
    signable
    -1.18
    ícias
    -1.16
    нодоро
    -1.16
    hers
    -1.11
    datable
    -1.10
    umers
    -1.08
    tocks
    -1.07
     ибо
    -1.06
    POSITIVE LOGITS
     one
    1.14
     by
    1.13
     famous
    1.10
     of
    1.09
     the
    1.06
    関連リンク
    1.03
    驚く
    1.03
    wavering
    1.01
     alemão
    0.98
    relenting
    0.98
    Activations Density 0.026%

    No Known Activations