© 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. 54235
    Prev
    Next
    INDEX
    Explanations

    New York or historical references

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

    categorizing by scale or type

    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
    Workflow
    0.49
    逦
    0.49
    之前
    0.49
     करेगी
    0.46
     Workflow
    0.46
     ใช้
    0.45
    嚮
    0.45
    網路
    0.45
    输入的
    0.45
    転職
    0.45
    POSITIVE LOGITS
     succeeded
    0.45
     persever
    0.45
     weil
    0.45
     neither
    0.45
     pesar
    0.44
     didn
    0.43
     sorted
    0.43
     responde
    0.42
     thickly
    0.42
     already
    0.41
    Activations Density 0.000%

    No Known Activations