© 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. 14689
    Prev
    Next
    INDEX
    Explanations

    continues, reaches, or remains

    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
     różne
    -1.03
     gekenn
    -1.00
     angefü
    -0.99
     detenido
    -0.98
    capace
    -0.96
     Въ
    -0.96
     are
    -0.94
     zaak
    -0.94
     popis
    -0.93
    火锅
    -0.93
    POSITIVE LOGITS
     diamantes
    1.22
     another
    1.19
     Fuerte
    1.10
     finally
    1.06
    женные
    1.05
     bringe
    1.05
     patatas
    1.04
     pleinement
    1.03
     continues
    0.98
    割合
    0.97
    Activations Density 0.042%

    No Known Activations