© 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. 2667
    Prev
    Next
    INDEX
    Explanations

    questions and answers ending in punctuation

    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
     större
    0.75
     whilst
    0.73
     hvilket
    0.73
     implying
    0.72
     einzelnen
    0.72
     Allowing
    0.71
     így
    0.70
     $-$
    0.69
     –
    0.68
     wsk
    0.67
    POSITIVE LOGITS
     hope
    0.95
    Dear
    0.92
    Hope
    0.91
    ^_^
    0.84
    。。
    0.84
     felicit
    0.83
     dear
    0.82
    hope
    0.82
     Hope
    0.82
    😍😍
    0.81
    Activations Density 0.106%

    No Known Activations