© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 80927
    Prev
    Next
    INDEX
    Explanations

    inventing unique things

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

    newest iPhones

    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
     Withers
    0.52
     clubes
    0.50
    اکہ
    0.50
    плы
    0.45
    Mig
    0.45
    衤
    0.45
    CMR
    0.45
     नंबर्स
    0.44
    हार
    0.44
    roč
    0.44
    POSITIVE LOGITS
     sphing
    0.54
     method
    0.48
    ำ
    0.47
     wordpress
    0.46
     Facebook
    0.45
     dataframe
    0.45
    活用
    0.44
     이용해서
    0.43
     Awakening
    0.43
    珑
    0.42
    Activations Density 0.000%

    No Known Activations