© 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. 10-GEMMASCOPE-RES-131K
    7. 45295
    Prev
    Next
    INDEX
    Explanations

    booking reservations

    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
    
    -2.39
    $^{\
    -2.30
    鼍
    -2.20
    degradable
    -2.14
    儅
    -2.13
    镠
    -2.11
    brackets
    -2.09
     ruines
    -2.08
     壁纸
    -2.08
     they
    -2.08
    POSITIVE LOGITS
     They
    2.77
    5
    2.72
    Both
    2.67
    This
    2.48
    From
    2.42
    -
    2.38
     Both
    2.36
    with
    2.36
    However
    2.34
    With
    2.31
    Activations Density 0.004%

    No Known Activations