© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19323
    Prev
    Next
    INDEX
    Explanations

    resource names and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    file and directory error handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     segmentation
    0.40
    </thead>
    0.38
     OUTPUT
    0.38
     Figs
    0.38
    ################
    0.37
     Output
    0.37
    ######
    0.37
     slant
    0.36
     Во
    0.36
     রচন
    0.36
    POSITIVE LOGITS
     bernama
    0.51
     بهذه
    0.47
     imbued
    0.46
    ที่มี
    0.46
    ՝
    0.45
     tenga
    0.43
     avec
    0.42
    ،
    0.41
     цієї
    0.41
     berjudul
    0.40
    Activations Density 0.001%

    No Known Activations