© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10758
    Prev
    Next
    INDEX
    Explanations

    want to thank/emphasize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     :=
    0.79
    )*(
    0.76
     назад
    0.74
    Details
    0.70
    стор
    0.70
    Eres
    0.69
    &*
    0.68
    zty
    0.67
    ✶
    0.67
    მო
    0.66
    POSITIVE LOGITS
     special
    1.53
     Special
    1.36
    special
    1.22
     shout
    1.21
    Special
    1.18
     SPECIAL
    1.15
     спеціа
    1.13
     Shout
    1.13
     специальных
    1.06
     shouts
    1.06
    Activations Density 0.055%

    No Known Activations