© 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. 8574
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    弓
    1.37
     gun
    1.28
     стре
    1.27
     shooters
    1.20
    guns
    1.20
     Shooting
    1.19
     shoot
    1.18
    Shoot
    1.17
    gun
    1.16
     guns
    1.15
    POSITIVE LOGITS
    嬸
    0.92
     CIP
    0.91
    萃
    0.87
     flip
    0.86
     tang
    0.84
     Zuckerberg
    0.83
     ম্যাগ
    0.82
    提取
    0.82
     alam
    0.81
     Magazine
    0.81
    Activations Density 0.083%

    No Known Activations