© 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. 6257
    Prev
    Next
    INDEX
    Explanations

    code saving instructions

    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
     being
    0.68
     चु
    0.63
     after
    0.62
     pu
    0.61
    شد
    0.59
     bou
    0.58
     بعد
    0.57
     –
    0.56
    being
    0.56
     beyond
    0.55
    POSITIVE LOGITS
     ಗೋ
    0.84
     Toán
    0.84
     majú
    0.82
     Herod
    0.82
     لینا
    0.81
     NSTX
    0.79
     disponibilidad
    0.79
    র্গে
    0.78
     Availability
    0.77
    砒
    0.76
    Activations Density 0.009%

    No Known Activations