© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 9751
    Prev
    Next
    INDEX
    Explanations

    acronyms and other ac- prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    र्गत
    0.43
     certains
    0.42
     necesario
    0.42
    𝘫
    0.41
     buoy
    0.40
    ാത്ത
    0.40
     certos
    0.39
    ameni
    0.39
    ovanje
    0.39
    ifaiFace
    0.39
    POSITIVE LOGITS
    Ac
    0.66
     AC
    0.59
     Ac
    0.57
     ac
    0.54
    ronym
    0.52
    <0x92>
    0.50
    AC
    0.46
    ademia
    0.46
    m
    0.44
    robat
    0.44
    Activations Density 0.057%

    No Known Activations