© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12281
    Prev
    Next
    INDEX
    Explanations

    how many / how much questions

    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_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     somehow
    1.19
     Somehow
    1.18
    anca
    1.13
    -.
    1.12
     Bantu
    1.08
     yok
    1.06
    erna
    1.06
     bakan
    1.06
    स्थल
    1.06
     wala
    1.05
    POSITIVE LOGITS
     زیادی
    1.45
     wynosi
    1.44
     proporcional
    1.43
     $|\
    1.37
     प्रमाणात
    1.32
    schnitt
    1.26
     vezes
    1.26
    દી
    1.24
    有多少
    1.24
    сць
    1.23
    Activations Density 0.485%

    No Known Activations