© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 555
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    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
    ,
    0.90
    :
    0.85
    ;
    0.63
    s
    0.63
    ،
    0.61
    :,
    0.59
     rectangular
    0.59
    =
    0.58
     first
    0.57
    :",
    0.57
    POSITIVE LOGITS
     Ironically
    1.09
     Natürlich
    1.08
     Finally
    1.07
     Lastly
    1.05
     Needless
    1.04
     Incidentally
    1.03
     Même
    1.02
     Кстати
    1.01
     Ultimately
    0.98
     Even
    0.98
    Activations Density 3.019%

    No Known Activations