© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7423
    Prev
    Next
    INDEX
    Explanations

    porous structure size surface

    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_12_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
    у
    1.73
    ed
    1.56
    HA
    1.39
    J
    1.39
    ub
    1.37
    ag
    1.35
    ş
    1.34
    very
    1.31
     Sementara
    1.30
    K
    1.30
    POSITIVE LOGITS
     opposites
    1.75
    ש
    1.62
     ambassadors
    1.57
    सलमान
    1.56
    फोल
    1.56
     observables
    1.49
     inadequ
    1.45
     unworthy
    1.45
    して
    1.44
     evils
    1.44
    Activations Density 0.001%

    No Known Activations