© 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. 33087
    Prev
    Next
    INDEX
    Explanations

    over to

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

    danger, risk, uncertainty, futures

    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
     dissimilar
    0.46
    מ
    0.45
    also
    0.44
     anche
    0.44
     cowardly
    0.44
    導致
    0.43
     jedoch
    0.43
     coward
    0.42
     ديال
    0.42
    最初に
    0.41
    POSITIVE LOGITS
    ৩৫
    0.46
     dziś
    0.45
    ...</
    0.45
     여섯
    0.45
    álni
    0.44
     ...");
    0.44
     ..$
    0.44
     '">'
    0.44
     //</
    0.44
    🚺
    0.43
    Activations Density 0.000%

    No Known Activations