© 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. 38698
    Prev
    Next
    INDEX
    Explanations

    help and support

    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
     have
    -0.93
     gjen
    -0.89
     will
    -0.85
    intervento
    -0.85
     brukt
    -0.84
     tilgjenge
    -0.82
     powiedział
    -0.81
    ஃ
    -0.81
    Attrib
    -0.81
     having
    -0.80
    POSITIVE LOGITS
    AFFIRMED
    1.03
    help
    0.98
     adegu
    0.98
     apoio
    0.97
     help
    0.97
     мере
    0.97
     нужда
    0.95
    ayuda
    0.94
     assistance
    0.92
     support
    0.91
    Activations Density 0.049%

    No Known Activations