© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9008
    Prev
    Next
    INDEX
    Explanations

    not doing or being

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

    not endorsing or intending

    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
    太多
    0.52
    Too
    0.50
     terlalu
    0.50
     слишком
    0.49
     too
    0.46
    too
    0.46
     anymore
    0.44
    太
    0.44
     zbyt
    0.44
    太大
    0.43
    POSITIVE LOGITS
     somehow
    0.84
     irgendwie
    0.67
     hề
    0.66
     Somehow
    0.65
     quelconque
    0.61
     whatsoever
    0.55
     endors
    0.51
     endorsement
    0.51
     quelcon
    0.51
     endorse
    0.50
    Activations Density 0.401%

    No Known Activations