© 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. 31750
    Prev
    Next
    INDEX
    Explanations

    made by

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

    caused by

    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
    0.68
    5
    0.64
     cuyo
    0.58
    3
    0.58
    6
    0.55
     což
    0.53
     așa
    0.52
    2
    0.52
    4
    0.52
     včetně
    0.51
    POSITIVE LOGITS
     terhadap
    0.68
     către
    0.54
     vegetation
    0.50
     människor
    0.50
     आतंकवाद
    0.48
     oleh
    0.48
     людьми
    0.48
     đối
    0.47
    անի
    0.46
     kepada
    0.45
    Activations Density 0.057%

    No Known Activations