© 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. 12767
    Prev
    Next
    INDEX
    Explanations

    ethical guidelines

    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
    DOWN
    2.57
    down
    2.34
    Down
    2.28
    ⁵
    2.28
     ³
    2.22
    Referring
    2.20
    شاء
    2.19
    ceaux
    2.19
    Though
    2.18
    ਹ
    2.18
    POSITIVE LOGITS
    gad
    2.42
    ктор
    2.39
    ഢ
    2.35
    guo
    2.35
    icionar
    2.33
    eep
    2.26
    স্তন
    2.14
    utung
    2.13
    ioen
    2.12
    anse
    2.12
    Activations Density 0.009%

    No Known Activations