© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1046
    Prev
    Next
    INDEX
    Explanations

    to be or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ly
    2.34
    вает
    2.17
    ъ
    2.16
    acle
    2.12
    giờ
    2.11
    ator
    2.05
    pal
    2.02
    ই
    1.99
    uge
    1.98
    ở
    1.97
    POSITIVE LOGITS
    ppling
    3.46
    ppled
    2.86
    ্তন
    2.56
    𝒐
    2.53
    彡
    2.46
    𝒖
    2.45
    ◸
    2.42
    lst
    2.34
    ffee
    2.33
    ed
    2.33
    Activations Density 1.540%

    No Known Activations