© 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. 34750
    Prev
    Next
    INDEX
    Explanations

    indices of properties

    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
    弊社
    -1.34
     cierta
    -1.16
     disparu
    -1.11
    鸲
    -1.09
    皆さま
    -1.06
     kolem
    -1.05
     alguma
    -1.04
    Trusted
    -1.04
     inmediato
    -1.02
    Manager
    -1.02
    POSITIVE LOGITS
     of
    1.74
     are
    1.56
     for
    1.37
     each
    1.29
     on
    1.19
    を
    1.07
     were
    1.07
     sowie
    1.05
    などを
    1.02
     in
    1.00
    Activations Density 0.218%

    No Known Activations