© 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. 44205
    Prev
    Next
    INDEX
    Explanations

    Gold, Ashanti, binding, ability

    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
    на
    1.39
    CE
    1.37
    ל
    1.37
    ă
    1.35
    א
    1.35
    ج
    1.34
    Р
    1.33
    ك
    1.30
    ق
    1.23
    𝐶
    1.23
    POSITIVE LOGITS
    sulf
    1.38
    tics
    1.36
    sning
    1.34
    sulph
    1.27
     substituents
    1.25
     bronchial
    1.23
     Shabd
    1.22
     tiet
    1.21
     Attractive
    1.16
     mattresses
    1.14
    Activations Density 0.002%

    No Known Activations