© 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. 33873
    Prev
    Next
    INDEX
    Explanations

    new object initialization

    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
    vore
    -0.89
    RectF
    -0.84
    koning
    -0.80
    ępu
    -0.80
    atific
    -0.79
    sco
    -0.78
     moo
    -0.77
    once
    -0.75
    祢
    -0.74
    MessageOf
    -0.73
    POSITIVE LOGITS
     آماده
    0.81
     prepares
    0.77
     vowed
    0.77
    準備
    0.75
    aság
    0.74
    剌
    0.74
     awaits
    0.73
     prepare
    0.71
     will
    0.71
     ready
    0.71
    Activations Density 0.023%

    No Known Activations