© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1337
    Prev
    Next
    INDEX
    Explanations

    scoring

    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
     दीपिका
    0.61
    Ƒ
    0.61
     పోలీ
    0.60
    velope
    0.60
    相位
    0.59
    utan
    0.59
     ք
    0.57
     ఇం
    0.57
     घु
    0.56
     মোক
    0.56
    POSITIVE LOGITS
     scoring
    0.59
     berry
    0.59
     jamb
    0.58
     mastic
    0.58
     essai
    0.56
     fru
    0.56
     चाहेंगे
    0.56
     saisir
    0.56
     पीछा
    0.55
    景区
    0.55
    Activations Density 0.521%

    No Known Activations