© 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. 73488
    Prev
    Next
    INDEX
    Explanations

    pull out

    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
    e
    -2.56
    .
    -2.42
    -2.27
    ↵↵
    -2.23
    O
    -2.20
    ed
    -2.16
    ]
    -2.11
    )
    -2.09
    for
    -2.06
    [
    -1.96
    POSITIVE LOGITS
    riezmann
    2.53
    zember
    2.30
    盦
    2.14
    playera
    2.11
    깽
    2.09
     größe
    2.06
     détaillée
    2.05
     daban
    2.02
    piej
    1.98
    
    1.98
    Activations Density 0.005%
    No Known Activations