© 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. 467
    Prev
    Next
    INDEX
    Explanations

    if-then conditions

    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
    ి
    1.17
    ات
    1.14
    ात्
    1.09
    йга
    1.07
    ‌ی
    1.00
    sels
    0.98
    rę
    0.97
    র্বর
    0.97
    lasting
    0.96
    鳞
    0.92
    POSITIVE LOGITS
    ary
    1.21
    ƌ
    1.19
    ek
    1.05
    Rig
    1.04
    머니
    1.01
    naire
    1.01
    MoO
    1.00
     кушымта
    0.99
    𝐚
    0.99
    𝐡
    0.98
    Activations Density 0.499%

    No Known Activations