© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8747
    Prev
    Next
    INDEX
    Explanations

    lesser degree

    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
    ዡ
    -3.05
    媜
    -2.81
    巿
    -2.75
    Ꮵ
    -2.72
    
    -2.63
    When
    -2.61
     lancar
    -2.59
    䛗
    -2.58
     processi
    -2.53
     strategis
    -2.53
    POSITIVE LOGITS
    )$
    2.66
     –
    2.41
     
    2.17
     lakini
    2.14
    на
    2.13
    
    2.09
    </em>
    2.06
    だが
    2.06
     $
    2.05
    缡
    2.05
    Activations Density 0.003%

    No Known Activations