© 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. 51242
    Prev
    Next
    INDEX
    Explanations

    bound and intersection

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

    explaining details and specifics

    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
     goTo
    0.46
     lowercase
    0.45
    历
    0.45
     kín
    0.44
    乐
    0.44
    创
    0.43
    合成
    0.43
    说
    0.42
     covalent
    0.42
    歴
    0.42
    POSITIVE LOGITS
     ascertaining
    0.48
    будь
    0.44
    preferably
    0.44
    resher
    0.43
    servic
    0.43
     Somalia
    0.43
     ڈیز
    0.43
    hopefully
    0.43
    ضافة
    0.42
    疎
    0.41
    Activations Density 0.000%

    No Known Activations