© 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. 189360
    Prev
    Next
    INDEX
    Explanations

    gps locations

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

    paid media marketing

    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
     .
    0.53
     banging
    0.53
    Assume
    0.50
    <start_of_image>
    0.49
     di
    0.48
     Assume
    0.46
     pounding
    0.45
    Find
    0.44
    o
    0.44
    ',
    0.43
    POSITIVE LOGITS
     예정
    0.52
     평
    0.51
     nirvach
    0.50
    奀
    0.49
     बेरोज
    0.48
     ऑफ़
    0.48
     अराज
    0.48
     측
    0.48
    shapeColor
    0.47
    luğu
    0.47
    Activations Density 0.001%

    No Known Activations