© 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. 693
    Prev
    Next
    INDEX
    Explanations

    you can

    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
     otherwise
    1.14
     if
    1.10
    不然
    1.01
    if
    0.95
    ?
    0.95
     later
    0.94
     it
    0.94
     vro
    0.94
    )
    0.93
     If
    0.93
    POSITIVE LOGITS
    ፩
    1.55
    둣
    1.48
    <unused2170>
    1.45
    <unused372>
    1.44
    នូវ
    1.43
    erdapat
    1.41
    <unused665>
    1.40
    ፴
    1.38
     memperoleh
    1.38
    产生了
    1.37
    Activations Density 0.929%

    No Known Activations