© 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. 22-GEMMASCOPE-RES-131K
    7. 84060
    Prev
    Next
    INDEX
    Explanations

    ball collision

    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
    ’
    -3.30
    </h5>
    -3.13
    </td>
    -2.78
    d
    -2.72
     —
    -2.66
    却又
    -2.63
     is
    -2.42
    if
    -2.42
    ']
    -2.34
    TryDecode
    -2.31
    POSITIVE LOGITS
    </strong>
    4.13
    鏷
    2.63
    ଝ
    2.55
    牁
    2.52
    2
    2.41
    淠
    2.38
    Ꮂ
    2.28
    
    2.25
    釤
    2.23
    utterstock
    2.22
    Activations Density 0.017%

    No Known Activations