© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33649
    Prev
    Next
    INDEX
    Explanations

    without or other

    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
    人和
    -0.96
     each
    -0.96
     chied
    -0.93
    Ikr
    -0.87
    onChangeText
    -0.85
     reversed
    -0.84
     these
    -0.82
     级
    -0.81
     rück
    -0.80
     perfeito
    -0.79
    POSITIVE LOGITS
     without
    1.98
     but
    1.84
    without
    1.41
     بدون
    1.34
     WITHOUT
    1.33
     tanpa
    1.29
    Without
    1.27
     χωρίς
    1.26
     ohne
    1.25
     other
    1.22
    Activations Density 0.086%

    No Known Activations