© 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. 9
    Prev
    Next
    INDEX
    Explanations

    I understand, I want, I recognize

    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
    s
    0.46
    A
    0.41
    ↵↵
    0.39
    C
    0.37
    a
    0.33
     звук
    0.31
    ς
    0.31
    n
    0.30
    c
    0.30
    P
    0.29
    POSITIVE LOGITS
     recommends
    0.43
     möchte
    0.42
     również
    0.41
     recommend
    0.41
     sẽ
    0.41
     recomienda
    0.41
     authorizes
    0.41
     berharap
    0.41
     couldn
    0.41
     undertook
    0.41
    Activations Density 0.621%

    No Known Activations