© 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. 7409
    Prev
    Next
    INDEX
    Explanations

    Re: followed by topic

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

    email subject lines

    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
    LookAndFeel
    0.47
    ിക്കും
    0.41
     Demp
    0.40
     MediaQuery
    0.40
    कर्म
    0.39
    OKR
    0.39
    準
    0.38
     Attendance
    0.38
     Karne
    0.38
    সং
    0.38
    POSITIVE LOGITS
    庀
    0.46
     The
    0.46
     जिज्ञा
    0.46
     ब्रैकेट
    0.46
     thomas
    0.45
    playlist
    0.45
    습니다
    0.44
     YOU
    0.44
     प्यार
    0.44
    stagram
    0.44
    Activations Density 0.003%

    No Known Activations