© 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. 39020
    Prev
    Next
    INDEX
    Explanations

    instantaneous change

    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
    </strong>
    -4.22
     ‘
    -2.77
    <td>
    -2.73
    ar
    -2.58
    </i>
    -2.53
     …
    -2.42
     “
    -2.42
    on
    -2.27
    </u>
    -2.19
     большого
    -2.14
    POSITIVE LOGITS
    इटम
    2.81
     russes
    2.64
     手機
    2.45
    茔
    2.45
     Muerte
    2.44
    ஂ
    2.42
    遹
    2.41
     Saltar
    2.39
     經
    2.38
    YNAMIC
    2.36
    Activations Density 0.002%

    No Known Activations