© 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. 10-GEMMASCOPE-RES-131K
    7. 60763
    Prev
    Next
    INDEX
    Explanations

    preparing dinner

    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_10/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
     both
    -1.98
     you
    -1.81
     these
    -1.52
    both
    -1.45
     będziesz
    -1.42
     even
    -1.41
     både
    -1.40
     I
    -1.40
     those
    -1.38
     a
    -1.36
    POSITIVE LOGITS
    czka
    1.41
    鸷
    1.30
     objectifs
    1.30
     Morte
    1.28
    ]$.
    1.27
    鹚
    1.22
     Vå
    1.21
     дальше
    1.21
    Gön
    1.21
    ladı
    1.20
    Activations Density 0.066%

    No Known Activations