© 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. 247332
    Prev
    Next
    INDEX
    Explanations

    financial aid lists

    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
     habt
    0.51
    ب
    0.50
     habíamos
    0.48
     multiplicar
    0.48
     avevano
    0.48
     withstood
    0.47
    দ্দি
    0.46
     cuantos
    0.46
     degrades
    0.45
     tinham
    0.45
    POSITIVE LOGITS
    daftar
    0.52
     พ
    0.50
    tao
    0.47
    tai
    0.47
    ፥
    0.46
    ją
    0.46
     εξ
    0.45
    interpret
    0.45
    acc
    0.45
    repeated
    0.45
    Activations Density 0.001%

    No Known Activations