© 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. 101986
    Prev
    Next
    INDEX
    Explanations

    supporter

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

    correlating brain activity

    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
    Your
    0.50
     Screening
    0.47
    Effects
    0.45
     Your
    0.44
     Rear
    0.44
     Drawing
    0.44
    ≪
    0.44
     کھولنے
    0.42
    HOM
    0.42
     還
    0.42
    POSITIVE LOGITS
     voisins
    0.52
     участников
    0.50
     protagonisti
    0.48
     доб
    0.47
     McPherson
    0.47
     socialista
    0.46
     wybor
    0.46
    mnopqrst
    0.46
    পন্থী
    0.46
     cyclones
    0.46
    Activations Density 0.001%

    No Known Activations