© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4799
    Prev
    Next
    INDEX
    Explanations

    Chinese, specific structures, comparative phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    <unused2145>
    0.68
    <unused2144>
    0.65
    <unused2124>
    0.63
    <unused2147>
    0.61
    藕
    0.60
    திக
    0.59
    िफिकेट
    0.58
    髋
    0.58
     අඩු
    0.58
    ቂያ
    0.57
    POSITIVE LOGITS
     S
    1.80
    S
    1.63
    SS
    1.48
     ス
    1.47
     SS
    1.44
    SA
    1.43
    SD
    1.42
    SI
    1.40
    SR
    1.38
    SL
    1.38
    Activations Density 5.885%

    No Known Activations