© 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. 112418
    Prev
    Next
    INDEX
    Explanations

    lame before were, medicine before t, traditionally before sourced

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

    counting words or numbers

    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
     Oké
    0.47
     ideales
    0.47
     spécifiques
    0.46
    (.*
    0.45
    DBOutput
    0.44
    cké
    0.44
    apa
    0.44
    idev
    0.44
    🫦
    0.44
    jm
    0.42
    POSITIVE LOGITS
     decline
    0.51
     watershed
    0.50
     loss
    0.48
     अंश
    0.46
     forfeiture
    0.46
     risk
    0.46
     lifespan
    0.45
     lifecycle
    0.45
     coinvol
    0.45
     midday
    0.45
    Activations Density 0.000%

    No Known Activations