© 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. 9153
    Prev
    Next
    INDEX
    Explanations

    identify potential, trends, gaps

    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
    ਂ
    2.17
    ædia
    2.12
    windowActionBar
    2.09
    ed
    2.07
    şan
    1.96
     lintas
    1.90
    addImage
    1.89
    iness
    1.85
    řed
    1.82
    ㅑ
    1.81
    POSITIVE LOGITS
    י
    2.73
    searchview
    2.61
    䡏
    2.47
    sans
    2.46
    distinct
    2.45
     Προ
    2.44
     counc
    2.41
    dé
    2.40
    sab
    2.40
    т
    2.39
    Activations Density 0.305%

    No Known Activations