© 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. 59616
    Prev
    Next
    INDEX
    Explanations

    planning, construction, management

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

    gas, iosis, length, skin

    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
    HasStarred
    0.48
    నే
    0.47
    㽞
    0.47
    ും
    0.46
     vendeurs
    0.46
    هما
    0.46
     اربعه
    0.45
    عليه
    0.45
     İst
    0.45
    ין
    0.44
    POSITIVE LOGITS
     de
    0.50
     vision
    0.48
     to
    0.43
     was
    0.42
    ক্তি
    0.40
    endl
    0.40
     ÷
    0.39
     outline
    0.39
     bullet
    0.39
     dislike
    0.38
    Activations Density 0.000%

    No Known Activations