© 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. 29-GEMMASCOPE-2-RES-65K
    7. 4060
    Prev
    Next
    INDEX
    Explanations

    business, manipulation, mitigation, insights, conspiracy, operations, analysis, manner, solidarity

    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_29_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
    (
    1.22
    '
    1.14
    :
    1.10
     এবং
    1.02
     and
    1.01
     ทั้ง
    0.95
    一个
    0.93
     でも
    0.92
    )
    0.90
    *:
    0.90
    POSITIVE LOGITS
    amp
    1.78
    ndash
    1.53
    mdash
    1.34
    ldquo
    1.23
    middot
    1.16
    Amp
    1.15
     somit
    1.10
    raquo
    1.09
    rarr
    0.99
    rdquo
    0.98
    Activations Density 0.181%

    No Known Activations