© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4029
    Prev
    Next
    INDEX
    Explanations

    maintaining balance coherence composure

    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
     Už
    1.04
     Pronto
    1.02
     soon
    1.01
    gete
    0.99
    <bos>
    0.99
     décrite
    0.97
     Kein
    0.95
    ités
    0.93
    终于
    0.90
    gen
    0.90
    POSITIVE LOGITS
    不变
    1.39
     유지
    1.24
     তব
    1.21
     composure
    1.19
     Ừ
    1.19
     steadfast
    1.18
    track
    1.16
     ανέ
    1.15
     unchanged
    1.14
     cordial
    1.12
    Activations Density 0.277%

    No Known Activations