© 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. 15294
    Prev
    Next
    INDEX
    Explanations

    locations and times

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

    different from

    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
     आपण
    0.44
     совокуп
    0.42
    ؎
    0.41
     पारस्परिक
    0.40
    ਾਨ
    0.39
    quate
    0.39
     Вас
    0.39
    с
    0.38
    worldly
    0.38
    vgl
    0.38
    POSITIVE LOGITS
     southernmost
    0.55
     areas
    0.51
     Areas
    0.51
    areas
    0.50
     একেবারে
    0.49
     endroits
    0.49
     शेवट
    0.49
    月份
    0.48
     leftmost
    0.48
     একদম
    0.48
    Activations Density 0.068%

    No Known Activations