© 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. 247938
    Prev
    Next
    INDEX
    Explanations

    important quadrant

    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
    g
    0.50
     온
    0.49
     cyclospor
    0.44
     ち
    0.44
     本
    0.44
     tally
    0.43
     nace
    0.43
     괴
    0.43
     심
    0.42
     trivia
    0.42
    POSITIVE LOGITS
    μου
    0.49
     adaption
    0.49
    াইয়৷
    0.46
    どのような
    0.46
    =>{
    0.46
    tarif
    0.45
     beforehand
    0.44
    どのように
    0.43
     ठाकरे
    0.43
    সভার
    0.43
    Activations Density 0.001%

    No Known Activations