© 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. 12629
    Prev
    Next
    INDEX
    Explanations

    detecting things

    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
    근
    2.30
    šć
    2.24
    adien
    2.19
    izal
    2.13
    얀
    2.13
    enl
    2.12
    igten
    2.11
    خصة
    2.10
    事的
    2.09
    jaer
    2.06
    POSITIVE LOGITS
     Trojans
    2.83
     alertas
    2.78
     Duplicate
    2.65
    🥯
    2.64
    🥭
    2.60
     Opinions
    2.60
     ouvrages
    2.60
     flashes
    2.59
    empor
    2.59
    rino
    2.58
    Activations Density 0.008%

    No Known Activations