© 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. 62920
    Prev
    Next
    INDEX
    Explanations

    to confer, The places, I had

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

    example

    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
    т
    0.45
     tỏ
    0.44
     separated
    0.43
    জিও
    0.43
    А
    0.42
    りたい
    0.42
    神通
    0.41
    ت
    0.41
    andolo
    0.41
     chiếc
    0.41
    POSITIVE LOGITS
     mRNAs
    0.41
     गैर
    0.41
     disebabkan
    0.41
     spowod
    0.41
    ਾਰੇ
    0.40
     directa
    0.40
    alcoholic
    0.40
    ("**
    0.40
     પડી
    0.39
     kvůli
    0.39
    Activations Density 0.000%

    No Known Activations