© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 990
    Prev
    Next
    INDEX
    Explanations

    mathematical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    en
    1.51
    ions
    1.25
    те
    1.13
    elling
    1.09
    ^{\
    1.07
    }\
    1.04
    agens
    1.03
    м
    1.02
    ъ
    1.00
    ch
    1.00
    POSITIVE LOGITS
     putchar
    1.33
     SF
    1.32
     ousted
    1.31
    cosity
    1.27
    fadeOut
    1.26
     Verständ
    1.26
    Adds
    1.25
     siRNA
    1.24
     biographer
    1.22
     Siem
    1.22
    Activations Density 0.000%

    No Known Activations