© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28517
    Prev
    Next
    INDEX
    Explanations

    Apple laptops and kingdoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    囫
    0.41
    вовано
    0.41
    鷸
    0.40
    HCO
    0.40
    simplified
    0.39
    묽
    0.39
    راتكم
    0.38
    蠹
    0.38
     Simplifying
    0.38
    ónicos
    0.38
    POSITIVE LOGITS
     leased
    0.48
     over
    0.45
     polled
    0.43
     other
    0.43
     wr
    0.43
     time
    0.42
     timeframe
    0.41
     equals
    0.41
     writs
    0.41
     only
    0.40
    Activations Density 0.000%

    No Known Activations