© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213985
    Prev
    Next
    INDEX
    Explanations

    lifting, flew, approach

    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
     parallelism
    0.42
    anatom
    0.39
    箒
    0.38
     впер
    0.38
     Hash
    0.37
     imbalance
    0.36
     outcrop
    0.36
    Hash
    0.36
     encounter
    0.35
     extracting
    0.35
    POSITIVE LOGITS
    కే
    0.46
    價
    0.43
    azionali
    0.40
     campanha
    0.39
     PRICES
    0.38
    ਵ
    0.38
    譙
    0.38
    ИН
    0.37
    諭
    0.37
     цены
    0.37
    Activations Density 0.002%

    No Known Activations