© 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. 200048
    Prev
    Next
    INDEX
    Explanations

    extremely successful

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

    Matching, delay, automatically generate

    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
    ﺪ
    0.66
     Герма
    0.55
    דים
    0.55
    דו
    0.54
    לו
    0.50
    Ка
    0.50
    ELER
    0.50
    ב
    0.50
    ניה
    0.49
    HAD
    0.49
    POSITIVE LOGITS
     postponement
    0.60
     settles
    0.58
     by
    0.50
     worsens
    0.50
     aversion
    0.49
     passage
    0.48
     imposes
    0.48
     for
    0.47
     asserts
    0.47
     rues
    0.47
    Activations Density 0.000%

    No Known Activations