© 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. 216400
    Prev
    Next
    INDEX
    Explanations

    actions ending in ing or ed

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

    country breakdowns instability

    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
    Eng
    0.47
    Prz
    0.47
    Jose
    0.46
    José
    0.46
    baptism
    0.46
    Dz
    0.45
    Bern
    0.45
    住
    0.45
    Kö
    0.44
    Charles
    0.44
    POSITIVE LOGITS
     monster
    0.45
     paire
    0.45
     ImageTk
    0.45
    细腻
    0.45
     kios
    0.44
     Kontext
    0.44
     ritmo
    0.43
     ulang
    0.43
     esigen
    0.43
     damos
    0.43
    Activations Density 0.004%

    No Known Activations