© 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. 23542
    Prev
    Next
    INDEX
    Explanations

    special sequence of words

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

    identifying fundamental potential

    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
    Drew
    0.41
     তাকে
    0.40
    客戶
    0.40
    DOCTYPE
    0.38
    讓人
    0.38
    챠
    0.38
     বাতাসে
    0.38
    (<
    0.38
    ที่เรา
    0.38
    EnglishMarks
    0.38
    POSITIVE LOGITS
    ەیە
    0.63
    ،
    0.47
    ifferent
    0.46
     respective
    0.46
     respectivas
    0.46
    ைகளில்
    0.46
    iophor
    0.46
    َی
    0.45
     Obj
    0.45
     respekt
    0.44
    Activations Density 0.000%

    No Known Activations