© 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. 188864
    Prev
    Next
    INDEX
    Explanations

    saving time and funds

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

    twin primes

    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
     நான்கு
    0.56
    тім
    0.55
    ícul
    0.52
     степен
    0.49
    ૯
    0.49
     இதே
    0.48
    യാള
    0.48
    കൊണ്ട്
    0.47
    <unused1640>
    0.46
    ús
    0.46
    POSITIVE LOGITS
     Bohemia
    0.49
     Genius
    0.45
     Einf
    0.45
     Mains
    0.45
     Alle
    0.44
     Mounting
    0.44
     Mx
    0.43
     Elba
    0.43
     Ein
    0.43
     Quand
    0.43
    Activations Density 0.000%

    No Known Activations