© 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. 71204
    Prev
    Next
    INDEX
    Explanations

    code keywords and assignments

    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
    quartier
    -1.02
     sudad
    -0.96
    everything
    -0.94
     rembourse
    -0.93
     maintenir
    -0.93
     werken
    -0.93
    äste
    -0.93
     adhesivo
    -0.93
    paket
    -0.92
    økt
    -0.92
    POSITIVE LOGITS
    ado
    0.92
    ksessa
    0.90
     should
    0.89
     from
    0.86
    ECTOR
    0.85
    u
    0.85
     one
    0.84
     }}$.
    0.81
     закри
    0.81
    }_{\
    0.80
    Activations Density 0.008%

    No Known Activations