© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14526
    Prev
    Next
    INDEX
    Explanations

    meanwhile ,

    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
    ت
    2.37
    rified
    2.11
    𝒐
    2.06
    yank
    2.03
     "<<
    2.01
    m
    2.00
    𝒆
    1.89
     **
    1.87
    pus
    1.84
    ..”
    1.84
    POSITIVE LOGITS
    гель
    3.05
    FlaskApp
    3.03
    ManagerState
    2.95
    LOADSTRING
    2.95
    ᒪ
    2.84
    Ꮋ
    2.84
    𝕟
    2.83
    Ᏼ
    2.81
     lucro
    2.78
     conférences
    2.78
    Activations Density 0.015%

    No Known Activations