© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1994
    Prev
    Next
    INDEX
    Explanations

    wikimedia images

    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_13_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
    en
    0.85
    ​​​​
    0.79
     ​​
    0.63
    的要求
    0.63
    ø
    0.63
    다
    0.60
     blowout
    0.59
     प्रतिनिधि
    0.59
    ियर
    0.58
    来进行
    0.58
    POSITIVE LOGITS
     chiefly
    1.23
     puisque
    1.12
    Như
    1.10
     avait
    1.10
    )(=
    1.10
     objeto
    1.09
     coseno
    1.09
     emplea
    1.09
     Chứng
    1.08
     principally
    1.08
    Activations Density 0.000%

    No Known Activations