© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8988
    Prev
    Next
    INDEX
    Explanations

    by followed by specific words

    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_13_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
    ة
    1.68
     buy
    1.61
    ViewGroup
    1.57
    or
    1.45
     dar
    1.45
    buyers
    1.45
     kamp
    1.43
    Meeting
    1.39
    Muk
    1.38
    ण
    1.36
    POSITIVE LOGITS
    zantine
    2.18
     virtue
    2.13
     dint
    1.88
    voorbeeld
    1.72
    rne
    1.67
     means
    1.66
     candlelight
    1.63
    gehend
    1.61
    Ꮔ
    1.60
    សារ
    1.60
    Activations Density 0.273%

    No Known Activations