© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93323
    Prev
    Next
    INDEX
    Explanations

    attempt to action

    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
    それでも
    -1.09
    能让
    -1.05
    有時
    -1.02
    áře
    -1.02
     טע
    -0.98
    čně
    -0.97
    '])
    -0.95
    それも
    -0.94
    見到
    -0.93
     liefern
    -0.93
    POSITIVE LOGITS
     Anschluss
    1.02
     når
    0.97
    凳
    0.93
     toutes
    0.91
     PROVISIONS
    0.89
    的一切
    0.88
     by
    0.88
    nung
    0.86
     Tries
    0.86
    tempted
    0.86
    Activations Density 0.035%

    No Known Activations