© 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. 13834
    Prev
    Next
    INDEX
    Explanations

    titles of books or shows

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

    technical terms or acronym starts

    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
    스를
    0.44
    ઞ
    0.39
    ્વાસ
    0.38
     glaube
    0.38
     നമഃ
    0.37
     aastal
    0.37
    ೨
    0.37
    ፩
    0.37
    ௭
    0.37
    煕
    0.37
    POSITIVE LOGITS
    parking
    0.39
    ’
    0.38
    font
    0.35
    url
    0.35
    and
    0.34
    hashtag
    0.34
    cknowled
    0.34
    recyclerview
    0.34
    themes
    0.33
    ardır
    0.33
    Activations Density 0.148%

    No Known Activations