© 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. 232011
    Prev
    Next
    INDEX
    Explanations

    taking the blame

    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
     do
    0.57
    و
    0.55
     rotary
    0.52
     divided
    0.50
     Lancet
    0.49
     symmetrical
    0.49
     LANC
    0.49
    １
    0.49
     FAR
    0.48
     differential
    0.48
    POSITIVE LOGITS
     afgelopen
    0.61
     소비자
    0.56
    ähne
    0.52
    trails
    0.52
    nem
    0.52
     zusätzlich
    0.52
     hätten
    0.52
     hätte
    0.51
     nieuws
    0.51
    izeit
    0.50
    Activations Density 0.000%

    No Known Activations