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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12107
    Prev
    Next
    INDEX
    Explanations

    efficiency and commission

    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
     "
    1.51
     break
    1.42
     negative
    1.41
    1.40
     score
    1.39
     written
    1.38
     none
    1.38
     denoting
    1.37
     read
    1.34
    "
    1.33
    POSITIVE LOGITS
    𝚄
    2.52
    鉻
    2.38
     paesi
    2.32
    Từ
    2.28
    MAPb
    2.26
    ीडियो
    2.23
    Municipio
    2.16
    Bộ
    2.15
     artesan
    2.15
     indígenas
    2.14
    Activations Density 0.030%

    No Known Activations