© 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. 156345
    Prev
    Next
    INDEX
    Explanations

    Armenian experience, more gratitude, your financial

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

    professional descriptions

    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
     collega
    0.47
     stalking
    0.44
     примене
    0.44
    েরও
    0.44
    時期
    0.44
     conecta
    0.44
     Sơn
    0.43
    횐
    0.43
    </h4>
    0.42
    ເວລາ
    0.42
    POSITIVE LOGITS
    ாகு
    0.51
    enary
    0.50
    PERATURE
    0.48
    emphas
    0.47
    al
    0.47
    ob
    0.46
    Catholic
    0.44
    on
    0.42
    kurat
    0.42
    Ό
    0.42
    Activations Density 0.001%

    No Known Activations