© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27590
    Prev
    Next
    INDEX
    Explanations

    customizing or dropdown

    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
     because
    -1.28
     this
    -1.24
     from
    -1.22
     karna
    -1.19
     évé
    -1.17
    ledad
    -1.16
     stringBuilder
    -1.15
     akku
    -1.13
     harap
    -1.13
     kapit
    -1.13
    POSITIVE LOGITS
     beantragt
    1.10
     있다
    1.08
    ógicas
    1.02
     secuencia
    1.02
    `.
    1.01
     artikkeli
    1.01
     berechnet
    1.00
    enumi
    1.00
    |$.
    0.99
    }
    
    0.98
    Activations Density 0.000%

    No Known Activations