© 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. 35181
    Prev
    Next
    INDEX
    Explanations

    form elements and labels

    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
     from
    -1.55
     to
    -1.48
    I
    -1.33
     it
    -1.27
     and
    -1.26
     a
    -1.24
    気に入りの
    -1.22
    𝐩
    -1.19
    ON
    -1.15
    '
    -1.13
    POSITIVE LOGITS
    もあって
    1.41
    比较好
    1.36
    Vegeta
    1.27
    がありますが
    1.27
     bloquer
    1.26
    焄
    1.24
    もあります
    1.23
    Legenda
    1.21
     chiffres
    1.21
    veloppe
    1.21
    Activations Density 0.001%

    No Known Activations