© 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. 10605
    Prev
    Next
    INDEX
    Explanations

    helpline

    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
    вища
    2.85
    @-
    2.53
    DL
    2.41
    rest
    2.32
    鵠
    2.28
    dl
    2.24
    Nos
    2.21
    downs
    2.21
     noodles
    2.20
    noodles
    2.18
    POSITIVE LOGITS
    ل
    4.23
            
    2.94
     bilo
    2.82
    ರಿದ
    2.81
    ليه
    2.78
    薈
    2.70
           
    2.69
    لې
    2.60
    ヂストン
    2.56
    ۲
    2.56
    Activations Density 0.030%

    No Known Activations