© 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. 109431
    Prev
    Next
    INDEX
    Explanations

    language and website information

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

    following "bad" or listing items

    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
     എന്റെ
    0.56
    ścic
    0.51
    }*/
    0.50
     താമസ
    0.49
     হারিয়ে
    0.48
    லைப்
    0.48
    掝
    0.48
     residente
    0.47
    ন্ত্রণ
    0.47
     క్యా
    0.47
    POSITIVE LOGITS
    рен
    0.51
     adduct
    0.50
     stade
    0.47
    риа
    0.47
     dialect
    0.44
     britannique
    0.44
    ր
    0.44
    γω
    0.44
    データベース
    0.43
    ның
    0.43
    Activations Density 0.002%

    No Known Activations