© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8546
    Prev
    Next
    INDEX
    Explanations

    referring to text sections

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

    CSS padding

    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_40_width_16k_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
     ANSWER
    0.40
    煐
    0.39
     활
    0.38
    要
    0.38
    ANS
    0.38
    禁
    0.37
    ント
    0.37
    Check
    0.37
    駄
    0.37
    ਸੀਂ
    0.36
    POSITIVE LOGITS
     text
    0.88
    Text
    0.78
     Text
    0.77
    text
    0.77
     текст
    0.76
     текста
    0.70
     texts
    0.67
     tekst
    0.67
     тексту
    0.66
     TEXT
    0.63
    Activations Density 0.013%

    No Known Activations