© 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. 209096
    Prev
    Next
    INDEX
    Explanations

    Osama bin Laden

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

    interactive activities, storytelling, 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
     historia
    0.55
     politik
    0.51
     ekonomi
    0.51
     iskust
    0.49
     sozialen
    0.49
    恪
    0.48
     FGD
    0.48
     sólo
    0.48
     én
    0.47
     demok
    0.47
    POSITIVE LOGITS
     notamment
    0.46
     distracting
    0.46
    ные
    0.45
    偶然
    0.44
    ためには
    0.43
    떄
    0.42
    额外的
    0.41
     hazardous
    0.41
     pesky
    0.41
    hazardous
    0.41
    Activations Density 0.001%

    No Known Activations