© 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. 34-GEMMASCOPE-RES-131K
    7. 94154
    Prev
    Next
    INDEX
    Explanations

    freeing up resources

    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_34/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
    エリー
    -0.74
    ственных
    -0.73
    ellum
    -0.72
    xbb
    -0.71
    usk
    -0.71
    ピ
    -0.70
    胱
    -0.70
    <>());
    -0.70
    つい
    -0.70
    linn
    -0.70
    POSITIVE LOGITS
     freeing
    5.47
     freed
    5.06
     frees
    4.81
     освобо
    4.09
    freed
    3.72
    frees
    3.42
     Freed
    3.27
     free
    3.08
     liberated
    2.91
     liberation
    2.88
    Activations Density 0.076%

    No Known Activations