© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15823
    Prev
    Next
    INDEX
    Explanations

    ob + suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    鶘
    0.63
     Mé
    0.56
     Bac
    0.54
     வடக்கு
    0.53
    Biografia
    0.52
     北
    0.52
    িস
    0.51
    کز
    0.51
     多
    0.50
     calyc
    0.50
    POSITIVE LOGITS
     ob
    0.93
     Ob
    0.85
    cob
    0.79
    Ob
    0.79
    об
    0.70
    solete
    0.70
     OB
    0.70
    vious
    0.69
     Obit
    0.68
     obs
    0.67
    Activations Density 0.107%

    No Known Activations