© 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. 209474
    Prev
    Next
    INDEX
    Explanations

    sustainability environmental progress

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

    * ** writing **

    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
    тро
    0.50
     Originally
    0.46
    αλ
    0.46
    ران
    0.45
    တိ
    0.45
    㡴
    0.44
    ครัว
    0.43
    pik
    0.43
     Giveen
    0.43
    𝕞
    0.43
    POSITIVE LOGITS
     break
    0.48
     cascades
    0.47
     senin
    0.47
    हेलो
    0.47
     coincident
    0.46
     morphology
    0.46
     downed
    0.45
     cascade
    0.45
     tubular
    0.45
     disinfectant
    0.44
    Activations Density 0.001%

    No Known Activations