© 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. 43291
    Prev
    Next
    INDEX
    Explanations

    Raw, living, draggable

    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
    ⺝
    1.65
    ע
    1.49
    m
    1.48
     incidences
    1.42
     lobes
    1.41
     dichos
    1.37
     irradiation
    1.30
     magnetization
    1.29
     vines
    1.26
     annexation
    1.24
    POSITIVE LOGITS
    ię
    1.35
     وإ
    1.27
    ᾽
    1.26
    ים
    1.23
    ال
    1.21
    0
    1.21
     aperto
    1.20
    ʻ
    1.20
    ↻
    1.20
    ი
    1.18
    Activations Density 0.000%

    No Known Activations