© 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. 35128
    Prev
    Next
    INDEX
    Explanations

    dependent on context

    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
    ین
    1.04
    ский
    0.93
    IAN
    0.93
    ี
    0.90
    рное
    0.86
    ем
    0.86
    ینا
    0.86
    ловой
    0.86
    ﻟ
    0.86
    ным
    0.84
    POSITIVE LOGITS
    jalan
    0.96
     inférieures
    0.93
    ktor
    0.91
     relatifs
    0.91
     accompagnée
    0.91
     estimés
    0.90
     établir
    0.89
     établ
    0.86
     Cliquez
    0.86
     conséquent
    0.85
    Activations Density 0.000%

    No Known Activations