© 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. 17-GEMMASCOPE-2-RES-16K
    7. 6686
    Prev
    Next
    INDEX
    Explanations

    concluding words like therefore, hence, so

    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
    %
    0.74
    beg
    0.73
     include
    0.70
     cops
    0.69
    看过
    0.68
     first
    0.68
    ?
    0.67
    认知
    0.66
    ?:
    0.65
     includes
    0.64
    POSITIVE LOGITS
     Somit
    1.14
     Therefore
    1.13
     somit
    1.11
     Ainsi
    1.11
     Vậy
    1.07
    Therefore
    1.03
     Hence
    1.02
     Jadi
    0.96
    Hence
    0.96
     therefor
    0.96
    Activations Density 0.448%

    No Known Activations