© 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. 67613
    Prev
    Next
    INDEX
    Explanations

    IPO, stock offerings

    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
    This
    -3.23
    It
    -3.22
    Any
    -2.94
    That
    -2.94
     —
    -2.78
     To
    -2.69
    You
    -2.67
    With
    -2.66
    酝
    -2.63
    </td>
    -2.61
    POSITIVE LOGITS
    蹰
    2.70
     faſt
    2.59
    
    2.45
     praktisch
    2.45
    歘
    2.44
     سرعت
    2.44
     tutup
    2.44
    趿
    2.42
     seguras
    2.42
     perak
    2.41
    Activations Density 0.002%

    No Known Activations