© 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. 7516
    Prev
    Next
    INDEX
    Explanations

    actual/real

    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
    यास
    0.66
    olm
    0.64
    nungs
    0.63
     మీడి
    0.62
    其次
    0.61
    ठान
    0.60
    bedarf
    0.59
    ဣ
    0.59
     vn
    0.59
    nment
    0.58
    POSITIVE LOGITS
     real
    4.03
    真正的
    3.97
     actual
    3.96
    真实的
    3.67
    真实
    3.62
    actual
    3.59
     واقعی
    3.59
    real
    3.51
     실제
    3.46
    Actual
    3.45
    Activations Density 1.085%

    No Known Activations