© 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. 179580
    Prev
    Next
    INDEX
    Explanations

    agent only, Holmes seconded, developments such

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

    everything or clear

    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
    是
    0.51
    /
    0.49
    는
    0.45
     Portfolio
    0.44
    您
    0.44
     units
    0.43
     donate
    0.42
     米
    0.42
     一般
    0.42
     effected
    0.42
    POSITIVE LOGITS
    منى
    0.47
    ţii
    0.47
    טת
    0.45
    turquoise
    0.45
    ተኛ
    0.45
     scheming
    0.45
     subtlety
    0.44
    namely
    0.43
    聝
    0.43
    getPassword
    0.43
    Activations Density 0.003%

    No Known Activations