© 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. 125065
    Prev
    Next
    INDEX
    Explanations

    providing information on future actions

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

    moving out from

    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
     warranted
    0.52
    രുവനന്തപു
    0.46
     avoided
    0.46
     decked
    0.45
    Ꭼ
    0.44
     hampered
    0.44
    (&
    0.43
    रावट
    0.43
    にかけて
    0.43
     opposition
    0.42
    POSITIVE LOGITS
     서비스를
    0.46
    و
    0.46
    盃
    0.46
    rie
    0.44
    Fried
    0.44
     نتائج
    0.44
     બીજા
    0.44
     ಉತ್ಪ
    0.44
    oua
    0.43
     باشه
    0.43
    Activations Density 0.001%

    No Known Activations