© 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. 67027
    Prev
    Next
    INDEX
    Explanations

    waiting forman calledhim<?phpRe:

    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
     we
    -1.63
     naše
    -1.52
     často
    -1.49
     imágen
    -1.48
     souvent
    -1.48
    ğimiz
    -1.45
    বং
    -1.45
     และ
    -1.42
     Vám
    -1.42
     également
    -1.38
    POSITIVE LOGITS
     without
    1.56
     his
    1.52
     doubtless
    1.45
     parcheggio
    1.44
     useless
    1.41
     himself
    1.38
     niega
    1.35
     surla
    1.35
     had
    1.34
    ᾷ
    1.34
    Activations Density 0.016%

    No Known Activations