© 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. 27076
    Prev
    Next
    INDEX
    Explanations

    end of sentence 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_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
    beiten
    -1.06
     bijvoorbeeld
    -1.05
    仍
    -1.04
    の場合は
    -1.03
    ponses
    -1.02
    ︠
    -1.02
     subsequence
    -1.02
     például
    -0.98
    სქოლიო
    -0.98
    tences
    -0.98
    POSITIVE LOGITS
     mengumumkan
    1.12
    それぞれの
    1.08
    ducers
    1.04
    {?>
    1.04
     size
    1.03
     differences
    0.98
    žite
    0.98
     renovar
    0.96
     anunció
    0.95
     cruda
    0.95
    Activations Density 0.040%

    No Known Activations