© 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. 210865
    Prev
    Next
    INDEX
    Explanations

    announcement of, announcement, announcement of the

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

    report the truth

    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
     менее
    0.55
    ोस
    0.50
     पुस्त
    0.49
     ક
    0.48
     החד
    0.48
    ่อย
    0.47
    攒
    0.47
    सीएस
    0.47
    ໂດ
    0.47
     জ
    0.47
    POSITIVE LOGITS
    withstanding
    0.50
     plight
    0.46
     Strecke
    0.45
     border
    0.45
    politics
    0.45
     territorial
    0.43
     angels
    0.43
    맑
    0.43
    ďaka
    0.42
     patriots
    0.42
    Activations Density 0.001%

    No Known Activations