© 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. 11461
    Prev
    Next
    INDEX
    Explanations

    strict rules and policies

    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
     }},
    3.18
    𝐡
    3.03
     }}\
    2.90
    龶
    2.87
    𝐢
    2.84
    𝐚
    2.82
    䣰
    2.81
    吘
    2.75
    𝐮
    2.68
     }}=
    2.68
    POSITIVE LOGITS
     det
    2.36
    pered
    2.33
    깐
    2.23
    ਿਆ
    2.19
     rd
    2.03
     st
    2.03
    ç
    1.99
     ‘
    1.97
    boxylic
    1.95
    abung
    1.95
    Activations Density 0.007%

    No Known Activations