© 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. 32049
    Prev
    Next
    INDEX
    Explanations

    albeit, admittedly, with qualifications

    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
    sing
    1.39
    ों
    1.37
    g
    1.35
    d
    1.27
    nt
    1.25
    sels
    1.25
    ή
    1.25
     dites
    1.24
    ClFN
    1.23
    ang
    1.22
    POSITIVE LOGITS
    な
    1.42
     أيضاً
    1.34
    esque
    1.32
    ে
    1.32
    ி
    1.32
     आफ्
    1.27
     immensely
    1.27
    chaft
    1.23
    etary
    1.23
    ем
    1.22
    Activations Density 0.001%

    No Known Activations