© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9323
    Prev
    Next
    INDEX
    Explanations

    create account

    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
    ฎ
    0.95
     decryption
    0.92
     remis
    0.92
    decompose
    0.89
     mutated
    0.88
     결방
    0.88
    圧
    0.88
    decrypt
    0.88
     variant
    0.86
    압
    0.83
    POSITIVE LOGITS
     create
    2.03
     creating
    1.99
    create
    1.94
     registering
    1.93
    Create
    1.92
     créer
    1.91
     Create
    1.89
    creating
    1.88
     Creating
    1.87
    Creating
    1.86
    Activations Density 0.448%

    No Known Activations