© 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. 34-GEMMASCOPE-RES-131K
    7. 76772
    Prev
    Next
    INDEX
    Explanations

    names after "that" or punctuation

    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_34/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
    拢
    -1.33
    าสตร์
    -1.23
    fordable
    -1.20
     těchto
    -1.19
     \%}$
    -1.14
     clôture
    -1.13
     ワンピース
    -1.10
     tâche
    -1.09
    INDICE
    -1.09
    thentic
    -1.08
    POSITIVE LOGITS
    2
    1.29
    1
    1.11
    össä
    1.09
    5
    1.05
     both
    1.05
    6
    1.04
     valuable
    1.03
    3
    1.02
    7
    1.01
    4
    0.98
    Activations Density 0.214%

    No Known Activations