© 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. 14760
    Prev
    Next
    INDEX
    Explanations

    .com / .net / .in

    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
     (
    -1.20
    
    -1.14
    РС
    -1.09
    assertThrows
    -1.08
    她就
    -1.07
    startY
    -1.05
    </em>
    -1.05
     mostrando
    -1.05
     então
    -1.03
    Predecesor
    -1.02
    POSITIVE LOGITS
     and
    1.33
    兩個
    1.24
    Arbe
    1.15
     soggior
    1.14
    كيفية
    1.13
    Ikke
    1.10
    あなたは
    1.09
     jemals
    1.09
    primera
    1.09
    problemas
    1.07
    Activations Density 0.000%

    No Known Activations