© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10635
    Prev
    Next
    INDEX
    Explanations

    observation effects on states

    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
    fl
    1.40
     ihe
    1.39
    )".
    1.35
    Ɵ
    1.28
     apni
    1.27
    )”.
    1.24
    dfrac
    1.20
     beschik
    1.19
     nigga
    1.16
    Nt
    1.15
    POSITIVE LOGITS
    </h1>
    1.10
     《
    1.04
    <h1>
    1.03
    <eos>
    0.92
     ※
    0.89
     ღ
    0.88
     */;
    0.86
     ха
    0.86
     с
    0.84
     』
    0.84
    Activations Density 0.116%

    No Known Activations