© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4059
    Prev
    Next
    INDEX
    Explanations

    elephant sanctuaries, shows, or actions

    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
    з
    1.91
    तम
    1.65
    thed
    1.62
    ções
    1.60
    eer
    1.60
    ս
    1.59
    een
    1.57
    ture
    1.55
    스와
    1.50
    스를
    1.48
    POSITIVE LOGITS
     extremism
    1.81
    Само
    1.79
     predicates
    1.77
     weakens
    1.72
    ﻖ
    1.69
     affidavits
    1.68
     rehearsals
    1.67
     hinders
    1.60
    ﺢ
    1.60
     enthalpies
    1.59
    Activations Density 0.001%

    No Known Activations