© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 359
    Prev
    Next
    INDEX
    Explanations

    names starting with robert

    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_13_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
    zigzag
    0.71
     ту
    0.71
    ЕД
    0.70
     katva
    0.70
    satisf
    0.68
     skul
    0.68
     extraneous
    0.67
    /=
    0.67
    =====
    0.67
     недо
    0.66
    POSITIVE LOGITS
     mahasiswa
    1.20
     selaku
    1.19
     mengatakan
    1.16
     rekan
    1.13
     colaboradores
    1.13
     Fellows
    1.11
     remaja
    1.11
     penulis
    1.09
     Inggris
    1.08
     menikah
    1.07
    Activations Density 0.552%

    No Known Activations