© 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. 150673
    Prev
    Next
    INDEX
    Explanations

    medical consultation, renovation projects, baking terms

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

    seeking shade or coolness

    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
     Whatsapp
    0.51
    狒
    0.47
     попа
    0.45
     мате
    0.45
    っぽ
    0.45
     Result
    0.45
    derr
    0.44
     मैथमेट
    0.44
     probleme
    0.44
     тексто
    0.44
    POSITIVE LOGITS
     expenditures
    0.51
     crescimento
    0.48
     abrasion
    0.47
    ScrollBar
    0.46
    வ
    0.46
     elastin
    0.45
     acres
    0.45
     penetrates
    0.43
     exportation
    0.43
    ARDS
    0.43
    Activations Density 0.000%

    No Known Activations