© 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. 222850
    Prev
    Next
    INDEX
    Explanations

    political, Azrael, Yoga

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

    place names and historical events

    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
     เดียว
    0.53
     または
    0.49
     الواحده
    0.48
     sagt
    0.47
     thorough
    0.46
     bulkhead
    0.44
     )
    0.44
     ,
    0.43
     および
    0.43
     Dict
    0.42
    POSITIVE LOGITS
    ഇ
    0.52
    就不会
    0.49
    വ്ര
    0.48
    zé
    0.47
     POLIT
    0.46
     POLITICAL
    0.46
    ᱵ
    0.46
     паліты
    0.45
    தமிழ்
    0.45
     político
    0.45
    Activations Density 0.000%

    No Known Activations