© 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. 44908
    Prev
    Next
    INDEX
    Explanations

    geographic locations and events

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

    text formatting and structure

    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
    lessness
    0.55
    hashtag
    0.54
    continu
    0.52
     haught
    0.51
    political
    0.50
    polit
    0.48
    𝗱
    0.48
    Н
    0.47
    ism
    0.47
    nom
    0.46
    POSITIVE LOGITS
     Fibre
    0.52
     Ebay
    0.50
     Hydro
    0.50
     ebay
    0.49
     refurbished
    0.48
     Irrigation
    0.47
     Prostate
    0.47
     refurb
    0.47
     eBay
    0.46
     our
    0.45
    Activations Density 0.000%

    No Known Activations