© 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. 153885
    Prev
    Next
    INDEX
    Explanations

    following certain nouns

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

    sequentially guiding fortress achieved

    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
    ches
    0.61
    have
    0.60
     م
    0.55
    having
    0.55
     اشاره
    0.55
    za
    0.54
    nytimes
    0.52
     المه
    0.52
    the
    0.51
     تابع
    0.50
    POSITIVE LOGITS
     erect
    0.49
     horrors
    0.47
     সক্র
    0.46
     tombs
    0.45
     octagon
    0.44
    廟
    0.44
     ?"
    0.44
     import
    0.43
     "").
    0.42
     FILES
    0.42
    Activations Density 0.000%

    No Known Activations