© 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. 67046
    Prev
    Next
    INDEX
    Explanations

    links and references

    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
    Datuak
    -0.98
     officio
    -0.97
     poiché
    -0.97
     deutschland
    -0.96
     Werke
    -0.96
     vermo
    -0.95
    lliant
    -0.95
    surgery
    -0.94
    enuta
    -0.94
     we
    -0.93
    POSITIVE LOGITS
     my
    1.92
    Ἁ
    1.18
    私の
    1.10
     Tienen
    1.05
     miei
    1.05
     hopefully
    1.04
     אני
    1.02
    elser
    1.02
    Недостатки
    1.01
     Esses
    1.01
    Activations Density 0.068%

    No Known Activations