© 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. 104500
    Prev
    Next
    INDEX
    Explanations

    find your emails tickets chronic unilateral

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

    recognizing patterns

    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
    POS
    0.47
    ٹ
    0.44
     is
    0.43
    ೀರ್
    0.43
     reconstruction
    0.42
     কিং
    0.42
     ē
    0.42
    ntgen
    0.42
     increases
    0.41
    sister
    0.41
    POSITIVE LOGITS
    చర్
    0.43
    టీఎం
    0.43
     studierte
    0.41
    ovej
    0.41
    逾
    0.41
    的能力
    0.40
     смогли
    0.40
    和社会
    0.40
    eged
    0.39
     assoc
    0.39
    Activations Density 0.000%

    No Known Activations