© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3424
    Prev
    Next
    INDEX
    Explanations

    d)

    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_17_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
     Nếu
    1.18
     Если
    1.12
     ifstream
    1.09
     ReturnVal
    1.09
     Exponential
    1.08
    Btns
    1.07
    萛
    1.06
     如果
    1.06
     Dacă
    1.06
     若
    1.05
    POSITIVE LOGITS
     er
    0.89
    ids
    0.75
    ý
    0.74
    ford
    0.73
    iding
    0.73
    름
    0.68
    fers
    0.68
    포
    0.68
    lei
    0.68
    ói
    0.67
    Activations Density 0.086%

    No Known Activations