© 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. 10626
    Prev
    Next
    INDEX
    Explanations

    financial, election, write, business

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

    exchange, therapy, 3d, 2005, coc, all, amm, Daniel, the

    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
     See
    0.55
     this
    0.50
     In
    0.48
     An
    0.48
    ↵
    0.47
     Learn
    0.47
     Whilst
    0.45
     Understand
    0.45
    ist
    0.44
    ↵↵
    0.44
    POSITIVE LOGITS
    לו
    0.47
     bactéries
    0.45
    THEOREM
    0.45
    윙
    0.43
    گرام
    0.40
    Ла
    0.40
    quasar
    0.40
     reunir
    0.40
     putern
    0.39
    ᱔
    0.39
    Activations Density 0.000%

    No Known Activations