© 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. 22-GEMMASCOPE-2-RES-16K
    7. 5920
    Prev
    Next
    INDEX
    Explanations

    watch?v= links

    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
     sone
    0.62
    禅
    0.59
    Mostly
    0.59
    ياة
    0.58
    வனி
    0.58
    iteur
    0.55
    onti
    0.54
     cant
    0.53
    bons
    0.53
     ens
    0.53
    POSITIVE LOGITS
     প্ৰ
    0.73
    룀
    0.70
     প্রান্ত
    0.70
     disciples
    0.70
     مذہبی
    0.69
    ಪ
    0.69
    মিনা
    0.68
     Salford
    0.68
     фаразы
    0.68
     전
    0.67
    Activations Density 0.061%

    No Known Activations