© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1587
    Prev
    Next
    INDEX
    Explanations

    command line option descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    Platz
    0.58
     Countess
    0.57
    닷
    0.56
     bearded
    0.56
     Chine
    0.55
     가진
    0.55
     Stump
    0.54
     사건
    0.54
    穣
    0.54
    vej
    0.53
    POSITIVE LOGITS
    设置为
    1.64
     toggle
    1.56
     togg
    1.55
     enabled
    1.51
     settings
    1.41
     설정
    1.40
     Enabled
    1.40
    Enabled
    1.38
    enabled
    1.38
    設定
    1.38
    Activations Density 0.619%

    No Known Activations