© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 5811
    Prev
    Next
    INDEX
    Explanations

    wide variety

    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
    ست
    1.91
    ㅠ
    1.91
    يي
    1.90
     annum
    1.87
    नंतर
    1.84
    lation
    1.82
     вдруг
    1.82
    ని
    1.81
    ların
    1.81
    нку
    1.80
    POSITIVE LOGITS
    uje
    2.13
    s
    1.98
     rãi
    1.86
    ul
    1.84
    aps
    1.64
    礪
    1.56
    anz
    1.53
    ين
    1.52
     zamanda
    1.52
    um
    1.50
    Activations Density 0.051%

    No Known Activations