© 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. 160879
    Prev
    Next
    INDEX
    Explanations

    striking depictions, defending against

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

    insurance, influence, developer, election, skull

    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
    ℎ
    0.52
     ту
    0.48
    glichkeiten
    0.47
    他的
    0.47
    nungen
    0.45
    Ns
    0.45
    фт
    0.44
    2
    0.44
     существенно
    0.44
    𝗻
    0.43
    POSITIVE LOGITS
     měst
    0.54
     bû
    0.54
     táct
    0.52
     lair
    0.51
     festa
    0.50
     talleres
    0.50
     estadística
    0.50
     alte
    0.49
     steals
    0.48
     salario
    0.48
    Activations Density 0.000%

    No Known Activations