© 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. 84322
    Prev
    Next
    INDEX
    Explanations

    direction toward or facing

    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
    <bos>
    -1.20
    <0xA3>
    -1.18
     in
    -1.14
    しかも
    -1.11
    CONCLUS
    -1.08
    的一个
    -1.08
     навіть
    -1.02
    茑
    -1.02
    これは
    -1.00
    紅葉
    -0.98
    POSITIVE LOGITS
     the
    1.88
     toward
    1.41
     towards
    1.41
    toward
    1.30
    towards
    1.23
    opposite
    1.19
     opposite
    1.11
    に向かって
    1.05
    へ向
    1.05
     hacia
    1.00
    Activations Density 0.018%

    No Known Activations