© 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. 44141
    Prev
    Next
    INDEX
    Explanations

    introduces questions or statements

    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
     of
    -2.48
    actéristi
    -2.47
     primeiras
    -2.45
    可以
    -2.44
    停下
    -2.41
     één
    -2.38
    -2.23
     doe
    -2.20
    卝
    -2.20
    </td>
    -2.19
    POSITIVE LOGITS
    that
    2.41
    餿
    2.34
    鰱
    2.27
    悒
    2.25
    硨
    2.25
    𓍯
    2.23
    梘
    2.17
    銲
    2.16
    ﮕ
    2.13
    }])
    2.11
    Activations Density 0.000%

    No Known Activations