© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65501
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
     there
    -1.36
     السيارات
    -1.30
    éu
    -1.23
    袒
    -1.21
    来到了
    -1.21
     meditación
    -1.21
     intenciones
    -1.12
    更快
    -1.05
     respiración
    -1.05
    zzato
    -1.05
    POSITIVE LOGITS
     your
    1.66
     if
    1.25
     for
    1.18
     preferably
    1.13
    ѕ
    1.13
    preferably
    1.12
     policiales
    1.11
     énergé
    1.10
     recommends
    1.10
     suggested
    1.10
    Activations Density 0.028%

    No Known Activations