© 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. 151840
    Prev
    Next
    INDEX
    Explanations

    apply image, lettering or decoration

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

    concepts like financial, metaverse, or events

    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
    =
    0.51
     dwie
    0.48
     jedna
    0.46
     aeruginosa
    0.43
     decays
    0.43
    のが
    0.43
    []=
    0.43
    ２
    0.42
     они
    0.42
     ஒன்று
    0.42
    POSITIVE LOGITS
     mortgage
    0.55
     financiero
    0.53
     pension
    0.50
     budgeting
    0.49
     cryptocurrency
    0.48
     pago
    0.48
     cinematic
    0.48
     dépenses
    0.48
     municipal
    0.48
     metaverse
    0.48
    Activations Density 0.000%

    No Known Activations