© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8107
    Prev
    Next
    INDEX
    Explanations

    numerical addresses

    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_22_width_65k_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
    Sexo
    0.86
     المحاضره
    0.82
    🚵
    0.75
     Bever
    0.74
     게시
    0.74
    笑道
    0.74
    🙍
    0.74
    ☣
    0.73
    eney
    0.73
     พื้น
    0.73
    POSITIVE LOGITS
    6
    1.24
    7
    1.22
    8
    1.16
    5
    1.14
    9
    1.13
    4
    1.11
    1
    1.09
    2
    1.07
    3
    1.06
    1.03
    Activations Density 0.024%

    No Known Activations