© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10697
    Prev
    Next
    INDEX
    Explanations

    instructionnext instructioncentersvelocity

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

    '> '

    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_40_width_16k_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
    imos
    0.44
    asto
    0.41
     Organization
    0.40
     Offenders
    0.39
     ऑर्गेनाइजेशन
    0.39
     विस्त
    0.38
    тем
    0.38
    撲
    0.38
    omos
    0.37
     Jurgen
    0.37
    POSITIVE LOGITS
     greek
    0.43
     egal
    0.40
     centres
    0.39
     centers
    0.39
     cavité
    0.39
    ,]$
    0.39
    ]]$
    0.38
     breakage
    0.38
    ნდა
    0.38
    CenterX
    0.37
    Activations Density 0.007%

    No Known Activations