© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3009
    Prev
    Next
    INDEX
    Explanations

    code output and results

    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
    िल्‍ली
    2.17
    ᠨ
    2.17
    𝗴
    2.10
    nö
    2.09
    sung
    2.04
     Stellen
    1.98
    ᵏ
    1.98
     Experimental
    1.97
    ρης
    1.97
    رسی
    1.96
    POSITIVE LOGITS
     misog
    1.83
     homophobic
    1.81
    !/"
    1.78
     cart
    1.78
     Hate
    1.77
    othed
    1.75
     heterosexual
    1.73
     soy
    1.71
     thumb
    1.71
    amethasone
    1.70
    Activations Density 0.126%

    No Known Activations