© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98121
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
     any
    -1.33
     perhaps
    -1.21
     this
    -1.20
     many
    -1.18
     other
    -1.16
     those
    -1.15
     each
    -1.14
     their
    -1.13
     some
    -1.06
     ketika
    -1.05
    POSITIVE LOGITS
     hesit
    1.18
     conquista
    1.15
    küche
    1.14
     butterknife
    1.14
    綜合報導
    1.10
     poten
    1.09
    şem
    1.09
     colheres
    1.08
     persecu
    1.07
     coronav
    1.07
    Activations Density 0.000%

    No Known Activations