© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1175
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives or participles

    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_7_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
    Fprintf
    2.72
    ра
    2.69
    كتر
    2.56
    ๅ
    2.51
    ান্য
    2.28
    ens
    2.24
    srand
    2.24
    ремя
    2.19
    рма
    2.19
     पड़े
    2.19
    POSITIVE LOGITS
    InChildren
    3.74
    #"
    2.66
    ÍA
    2.61
    "...
    2.60
    medallas
    2.55
    ജ്ഞ
    2.55
    Jackson
    2.51
    HJ
    2.49
    ﻬ
    2.46
    Ⅺ
    2.45
    Activations Density 0.505%

    No Known Activations