© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40482
    Prev
    Next
    INDEX
    Explanations

    blocks and motivation

    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
     reproach
    1.66
     narrative
    1.56
     political
    1.53
    ை
    1.52
     Fonts
    1.47
     pirate
    1.44
     toil
    1.44
     projectile
    1.38
     storefront
    1.35
    ible
    1.34
    POSITIVE LOGITS
    на
    2.08
    ন
    1.77
    ان
    1.63
    𝘩
    1.58
    ্পনিক
    1.55
    اي
    1.55
    ために
    1.52
    اً
    1.48
    dehyde
    1.47
    を通して
    1.46
    Activations Density 0.001%

    No Known Activations