© 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. 34-GEMMASCOPE-RES-131K
    7. 66053
    Prev
    Next
    INDEX
    Explanations

    introduction and question separators

    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
    やろ
    -1.07
     and
    -1.04
     characteristics
    -1.02
     csin
    -1.00
     because
    -1.00
     българ
    -0.98
     on
    -0.96
     under
    -0.96
    NSObject
    -0.95
     facilitate
    -0.94
    POSITIVE LOGITS
     dring
    1.15
     alcuni
    1.10
     crappy
    1.09
     Qaeda
    1.08
     Dennoch
    1.06
     alcune
    1.05
     dando
    1.05
     continuer
    1.04
     Dafür
    1.03
     nieuwe
    1.02
    Activations Density 0.002%

    No Known Activations