© 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. 39078
    Prev
    Next
    INDEX
    Explanations

    lesson worksheets

    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
     when
    -1.10
    žová
    -1.06
    dith
    -1.01
     précédentes
    -1.01
    لوب
    -1.00
    zando
    -0.98
    ABILIDAD
    -0.98
     our
    -0.97
    😲
    -0.96
     ${({
    -0.96
    POSITIVE LOGITS
     также
    1.28
     also
    1.26
    接过
    1.12
     también
    1.09
     também
    1.08
     certamen
    1.06
    สามารถ
    1.05
     задний
    1.05
     також
    1.04
     childish
    1.04
    Activations Density 0.021%

    No Known Activations