© 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. 5493
    Prev
    Next
    INDEX
    Explanations

    cor prefix

    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
     dismissed
    0.75
     considered
    0.71
     kamp
    0.71
     sobie
    0.67
     grasped
    0.66
    end
    0.66
    ⴷ
    0.66
     Considered
    0.65
    𝙴
    0.65
    ekan
    0.64
    POSITIVE LOGITS
    ث
    0.91
    ثة
    0.83
    家伙
    0.80
    otation
    0.79
     Darkness
    0.78
     eighteen
    0.76
    inth
    0.76
     మర
    0.76
     arte
    0.76
     Make
    0.75
    Activations Density 0.029%

    No Known Activations