© 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. 10-GEMMASCOPE-RES-131K
    7. 86776
    Prev
    Next
    INDEX
    Explanations

    movement and arrival

    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
     when
    -2.19
     through
    -1.73
    紝
    -1.63
    涐
    -1.55
    好評
    -1.51
     Lainnya
    -1.42
     Gouver
    -1.37
     until
    -1.37
     during
    -1.35
     Then
    -1.34
    POSITIVE LOGITS
    }
    1.91
    vidade
    1.70
    atized
    1.61
                
    1.59
     ARISING
    1.54
    usions
    1.47
    itize
    1.45
    ming
    1.45
    the
    1.44
    oping
    1.43
    Activations Density 0.020%

    No Known Activations