© 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. 66373
    Prev
    Next
    INDEX
    Explanations

    consumer sentiments

    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
     their
    -1.52
     for
    -1.29
     on
    -1.24
     using
    -1.23
     deliberately
    -1.04
     in
    -1.02
     or
    -1.01
    corrhi
    -1.00
     you
    -0.99
    ⿻
    -0.99
    POSITIVE LOGITS
    defined
    1.28
    ㄌ
    1.16
    などが
    1.16
     decorazione
    1.11
     microprocessor
    1.10
     stiefel
    1.09
     페이지
    1.07
    ㄋ
    1.06
    礒
    1.04
     ocas
    1.02
    Activations Density 0.000%

    No Known Activations