© 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. 91939
    Prev
    Next
    INDEX
    Explanations

    add to

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

    contextual modifiers

    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
    俄
    0.54
    soil
    0.51
    epit
    0.51
    jul
    0.49
    aj
    0.48
    nested
    0.48
    ken
    0.48
    filament
    0.48
    dirt
    0.47
    土
    0.47
    POSITIVE LOGITS
     upregulation
    0.49
     trustworthiness
    0.48
     dissonance
    0.46
     sympath
    0.46
    ل
    0.45
    ುನ
    0.44
     brevity
    0.44
     calyce
    0.43
     léz
    0.43
     tabulated
    0.43
    Activations Density 0.001%

    No Known Activations