© 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. 201144
    Prev
    Next
    INDEX
    Explanations

    wise enough connections

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

    concept and descriptor pairing

    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
    -
    0.52
    AreEqual
    0.46
    рев
    0.45
    Db
    0.45
    bib
    0.44
    ékek
    0.44
    baar
    0.43
    Cra
    0.42
    Phong
    0.41
    -[
    0.41
    POSITIVE LOGITS
     يساعد
    0.47
     Lipstick
    0.46
    𝘨
    0.45
     பெரும்பாலான
    0.45
     பரு
    0.44
     screwed
    0.44
     সবগুলো
    0.44
     ช่วย
    0.44
    োজিত
    0.44
     दिये
    0.43
    Activations Density 0.000%

    No Known Activations