© 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. 175732
    Prev
    Next
    INDEX
    Explanations

    . Your

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

    extravert, theory relies, sound symbolism

    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
    LOCK
    0.51
    STE
    0.50
     saranam
    0.50
    anager
    0.48
     cinq
    0.48
    １
    0.47
    SCR
    0.47
    ΜΑ
    0.47
    ”、
    0.46
     Lockwood
    0.46
    POSITIVE LOGITS
     Yeni
    0.48
     externa
    0.46
     Types
    0.46
     Oleh
    0.46
    Yeni
    0.44
    흡
    0.44
    phones
    0.44
    щики
    0.44
     Daftar
    0.44
     Type
    0.43
    Activations Density 0.001%

    No Known Activations