© 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. 44802
    Prev
    Next
    INDEX
    Explanations

    don't worry

    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
     kurzem
    -1.64
    poň
    -1.61
    baikan
    -1.49
    のサ
    -1.48
     вся
    -1.48
    แรก
    -1.48
     relacionadas
    -1.46
     späteren
    -1.41
    ffed
    -1.38
     feitas
    -1.37
    POSITIVE LOGITS
    \
    1.92
    ,
    1.77
    .
    1.76
    没有人
    1.63
     نامه
    1.60
    </tr>
    1.56
    斯克
    1.53
    Lol
    1.48
    </td>
    1.48
    s
    1.45
    Activations Density 0.001%

    No Known Activations