© 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. 7160
    Prev
    Next
    INDEX
    Explanations

    send followed by action or data

    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
     sole
    1.22
    old
    1.13
    о
    1.06
    িণ
    1.05
    ἓ
    1.04
    ancienne
    1.04
    Message
    1.04
     somehow
    1.03
     gamle
    0.94
    老
    0.93
    POSITIVE LOGITS
    มอบ
    1.41
     chills
    1.38
    recv
    1.34
    imental
    1.32
    wicklung
    1.30
    迎
    1.29
    vič
    1.27
     извест
    1.22
    idefinite
    1.19
    weisung
    1.19
    Activations Density 0.079%

    No Known Activations