© 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. 146242
    Prev
    Next
    INDEX
    Explanations

    love mercy and walk humbly

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

    time commitment and duration

    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
    Medieval
    0.47
    Engagement
    0.46
    Peaks
    0.43
    粉絲
    0.43
    อัน
    0.42
    险
    0.41
    oudre
    0.41
    घा
    0.41
    营收
    0.40
    培
    0.40
    POSITIVE LOGITS
    ınızı
    0.47
     Fortsch
    0.45
     ZO
    0.43
    myapp
    0.43
     पूरे
    0.43
     обычной
    0.42
     gymn
    0.42
     hakk
    0.41
     करवाने
    0.41
     Zum
    0.41
    Activations Density 0.011%

    No Known Activations