© 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. 29574
    Prev
    Next
    INDEX
    Explanations

    position tothank youself-believing

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

    concepts or states followed by specific domains

    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
     Srps
    0.49
    Ꮀ
    0.48
     Natl
    0.48
     agr
    0.47
     libras
    0.47
    悳
    0.46
    সহিত
    0.46
    ･
    0.46
     monopol
    0.46
    istem
    0.45
    POSITIVE LOGITS
     tetrahedron
    0.47
     مخطط
    0.45
     rectangular
    0.43
     molding
    0.40
    whale
    0.40
     tetrahedral
    0.40
    rectangular
    0.40
     campgrounds
    0.40
     multipurpose
    0.39
    キャンプ
    0.39
    Activations Density 0.000%

    No Known Activations