© 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. 122760
    Prev
    Next
    INDEX
    Explanations

    all costs

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

    don't underestimate or dislike

    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
     situés
    0.49
     cittadini
    0.49
     ব্লগার
    0.48
     मिक्स
    0.47
     echoed
    0.46
     zouden
    0.46
     brachte
    0.46
    偐
    0.46
     zadovol
    0.45
     ঠান্ডা
    0.45
    POSITIVE LOGITS
    hopefully
    0.56
    CLM
    0.53
    technology
    0.47
    CT
    0.47
    statistics
    0.47
     indel
    0.47
     it
    0.46
    thru
    0.46
    blind
    0.46
     ruthless
    0.45
    Activations Density 0.001%

    No Known Activations