© 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. 222785
    Prev
    Next
    INDEX
    Explanations

    location words

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

    continuation or response

    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
     simonsen
    0.50
    𝗯
    0.49
     cables
    0.47
     invoices
    0.47
     confid
    0.46
     fide
    0.46
     domicilio
    0.45
     proprietà
    0.45
    𝟮
    0.45
     retraining
    0.44
    POSITIVE LOGITS
     కేంద్ర
    0.44
     ফোর্স
    0.43
     উত্স
    0.43
     হাত
    0.42
    waitFor
    0.42
     اخیر
    0.41
     నుండి
    0.41
     Европы
    0.40
    axanthin
    0.40
     மேம்ப
    0.40
    Activations Density 0.002%

    No Known Activations