© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35115
    Prev
    Next
    INDEX
    Explanations

    async tasks and threads

    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
     każdej
    -1.16
     каждом
    -1.11
     cerdo
    -1.09
     câncer
    -1.09
    ționale
    -1.06
    γε
    -1.06
     restant
    -1.05
     offrant
    -1.05
     faciliter
    -1.02
    filtre
    -1.02
    POSITIVE LOGITS
     or
    1.23
     then
    1.23
    お願い
    1.15
    𝑔
    0.96
    andolo
    0.96
    ográfico
    0.94
     terribly
    0.93
     but
    0.93
     particularly
    0.92
    ieuses
    0.91
    Activations Density 0.009%

    No Known Activations