© 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. 22-GEMMASCOPE-RES-131K
    7. 15661
    Prev
    Next
    INDEX
    Explanations

    category following topic

    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_22/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
     other
    -1.23
    >
    -1.09
    何况
    -1.07
    但却
    -1.07
    つまり
    -1.06
    虽说
    -1.06
    </b>
    -1.03
    un
    -1.02
    ですが
    -1.01
     cantora
    -1.01
    POSITIVE LOGITS
     and
    1.65
     gekomen
    1.30
    geç
    1.23
    Źródło
    1.22
    Répondre
    1.20
    の方も
    1.19
     gemak
    1.18
    depuis
    1.18
     трябва
    1.16
     Dünya
    1.16
    Activations Density 0.073%

    No Known Activations