© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79576
    Prev
    Next
    INDEX
    Explanations

    library names (.hpp, fa, gtx, aws, plugin)

    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
     time
    -1.31
    "
    -1.20
     with
    -1.19
     "
    -1.17
     from
    -1.15
     here
    -1.13
     There
    -1.12
     break
    -1.12
    \
    -1.10
     one
    -1.08
    POSITIVE LOGITS
    ㄓ
    1.30
    仫
    1.27
    尨
    1.27
    羶
    1.26
     personnaliser
    1.20
     hik
    1.20
     iny
    1.19
     kod
    1.18
     noy
    1.18
     sasa
    1.16
    Activations Density 0.003%

    No Known Activations