© 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. 5258
    Prev
    Next
    INDEX
    Explanations

    consumer hardware

    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
     COST
    0.69
    omac
    0.68
     cost
    0.67
     cul
    0.66
    ូច
    0.65
     Cost
    0.64
    /$
    0.62
    )-$
    0.60
    cost
    0.59
    ويلة
    0.59
    POSITIVE LOGITS
     информа
    0.75
     personenbez
    0.73
     GDPR
    0.72
    Google
    0.71
     gouvernement
    0.71
     સ્પ
    0.70
     confusing
    0.68
     navigational
    0.68
    间
    0.67
     দপ্তর
    0.67
    Activations Density 0.093%

    No Known Activations