© 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. 144849
    Prev
    Next
    INDEX
    Explanations

    that show

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

    ID, verification, access, wishes

    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
    diaz
    0.60
     遅く
    0.60
     Bildschirm
    0.59
     아버지
    0.56
    ierzchn
    0.55
     Nxe
    0.55
    ।*
    0.55
    dzić
    0.55
     höchsten
    0.54
    lineEdit
    0.54
    POSITIVE LOGITS
    Produ
    0.54
    ens
    0.45
    Swap
    0.44
     totaled
    0.44
    0.44
    et
    0.43
     items
    0.43
    q
    0.43
    ised
    0.42
     ornamentation
    0.42
    Activations Density 0.000%

    No Known Activations