© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2672
    Prev
    Next
    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]++;
    0.95
     null
    0.84
     ?";
    0.81
    NotNull
    0.78
     indexOf
    0.77
    ++;
    0.77
     (++
    0.76
     Null
    0.75
    jLabel
    0.74
     NULL
    0.73
    POSITIVE LOGITS
    ({'
    1.55
    =[]
    1.47
    .__
    1.46
    =['
    1.43
    dict
    1.42
    =''
    1.41
    ()['
    1.41
    ={'
    1.37
     dict
    1.37
    kwargs
    1.36
    Activations Density 0.028%

    No Known Activations