© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3512
    Prev
    Next
    INDEX
    Explanations

    conjunctions or clauses

    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_29_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
    ،
    0.78
    ,
    0.63
    ，
    0.60
    、
    0.58
     ،
    0.57
     ఏమి
    0.53
    的是
    0.52
    ：
    0.52
    ፣
    0.50
    ával
    0.50
    POSITIVE LOGITS
     although
    1.11
     though
    1.03
     meaning
    0.97
    although
    0.94
     hence
    0.94
     making
    0.91
    though
    0.89
    hence
    0.89
    meaning
    0.88
     albeit
    0.83
    Activations Density 0.484%

    No Known Activations