© 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. 124998
    Prev
    Next
    INDEX
    Explanations

    book/folder/reference/topic context

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

    Arrivals, Costco, PHP, Bargain, infinite, Support

    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
     this
    0.43
    false
    0.43
    =
    0.42
    ț
    0.40
    amp
    0.40
     knowing
    0.39
    Compliance
    0.39
    b
    0.38
     a
    0.38
    this
    0.38
    POSITIVE LOGITS
     একেবারেই
    0.45
    俻
    0.43
     sahibi
    0.42
    䓶
    0.42
     சிறி
    0.42
    ເຄື່ອງ
    0.42
     متابعي
    0.42
    负责人
    0.41
    傃
    0.41
    㨁
    0.41
    Activations Density 0.001%

    No Known Activations