© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2305
    Prev
    Next
    INDEX
    Explanations

    suffixes like ized, itation, istic, ish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    o
    2.25
    를
    2.12
    י
    2.11
    к
    2.09
    ング
    2.07
    iunea
    1.93
    ки
    1.91
    ه
    1.90
    ة
    1.89
    تهم
    1.89
    POSITIVE LOGITS
    ized
    1.15
    itation
    1.09
    istic
    1.08
    static
    0.96
    ish
    0.95
    ificial
    0.95
     Shenzhen
    0.88
    itiveness
    0.88
    ists
    0.88
    phill
    0.87
    Activations Density 0.331%

    No Known Activations