© 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. 187755
    Prev
    Next
    INDEX
    Explanations

    listed below, medal, taurus touch, atv

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

    Provides context for `from`

    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
     surpre
    0.52
     interessante
    0.47
    ة
    0.47
     analis
    0.46
     lindo
    0.46
     interessant
    0.46
     vũ
    0.45
     GAR
    0.45
    ى
    0.45
     bals
    0.44
    POSITIVE LOGITS
    chained
    0.49
     chained
    0.48
    DLJ
    0.46
    К
    0.44
    professional
    0.43
    叱
    0.43
     PROFESSIONAL
    0.43
    つけた
    0.42
    чи
    0.41
     ಸದಸ್ಯ
    0.41
    Activations Density 0.000%

    No Known Activations