© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38490
    Prev
    Next
    INDEX
    Explanations

    Python syntax and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ywidual
    0.47
     হুমকির
    0.44
    DAAR
    0.44
    perluan
    0.43
    特定の
    0.43
    私は
    0.42
     각
    0.42
    ⟫
    0.41
    私が
    0.41
    asmim
    0.40
    POSITIVE LOGITS
     immobile
    0.44
     monotonous
    0.42
    ري
    0.42
     buying
    0.41
     ولكن
    0.41
     puddle
    0.41
     you
    0.40
     salt
    0.40
     exiting
    0.39
    n
    0.39
    Activations Density 0.012%

    No Known Activations