© 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. 7106
    Prev
    Next
    INDEX
    Explanations

    so you can find

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

    morally wrong

    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
    their
    0.51
    о
    0.50
    own
    0.47
    they
    0.47
    Ｖ
    0.45
    conver
    0.44
    ро
    0.43
    rews
    0.43
    eland
    0.43
     všetky
    0.43
    POSITIVE LOGITS
    🍢
    0.50
     ópt
    0.49
     Museums
    0.45
    ිරීම
    0.44
     Necklace
    0.44
     Museum
    0.44
     situé
    0.44
     ा
    0.43
    दर्शी
    0.43
     polarizing
    0.43
    Activations Density 0.000%

    No Known Activations