© 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. 21650
    Prev
    Next
    INDEX
    Explanations

    become a descriptor

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

    separate rows or tables

    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
    區
    0.49
     defend
    0.43
     workaround
    0.43
     groove
    0.43
     config
    0.42
    +\
    0.42
     ruins
    0.42
    ={\
    0.42
     que
    0.41
     snowy
    0.40
    POSITIVE LOGITS
     Александра
    0.56
    ﺍ
    0.55
    Australia
    0.53
    ᑲ
    0.51
    АР
    0.49
     ऑस्ट्रेलिया
    0.48
    Он
    0.47
     Australia
    0.47
    ْل
    0.47
     Австра
    0.46
    Activations Density 0.000%

    No Known Activations