© 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. 46430
    Prev
    Next
    INDEX
    Explanations

    you down, that modern, appointed insurance

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

    narrative structure, web screens, decisions made

    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
    Fiat
    0.55
    Benz
    0.55
    髑
    0.55
    חס
    0.51
    敉
    0.48
    effet
    0.48
    르
    0.48
    த
    0.47
    Mut
    0.47
    돛
    0.47
    POSITIVE LOGITS
     findest
    0.51
     geologist
    0.51
     maupun
    0.50
    বাসীর
    0.50
     পূ
    0.49
     potete
    0.49
     ஆகியவை
    0.48
     झाल्यानंतर
    0.47
     County
    0.47
     darauf
    0.47
    Activations Density 0.000%

    No Known Activations