© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9221
    Prev
    Next
    INDEX
    Explanations

    Low-Rank Adaptation

    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_22_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
    …
    0.99
    ーー
    0.92
     enchanted
    0.91
     drizz
    0.91
    ...
    0.89
     Wrath
    0.87
     vented
    0.85
     hudson
    0.84
     xsi
    0.84
    ……
    0.84
    POSITIVE LOGITS
    $^{
    1.90
    limit
    1.33
     博文
    1.29
    rapa
    1.25
    relationship
    1.21
    loch
    1.21
    relationships
    1.19
    lift
    1.18
    یکی
    1.18
    कै
    1.17
    Activations Density 0.085%

    No Known Activations