© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1378
    Prev
    Next
    INDEX
    Explanations

    break down

    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_13_width_65k_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
    iate
    1.51
    eal
    1.43
    evice
    1.38
    ea
    1.37
    iat
    1.34
    <bos>
    1.30
    eo
    1.27
    𝘀
    1.26
    hang
    1.25
    taste
    1.23
    POSITIVE LOGITS
     Grenzen
    1.34
    裟
    1.32
    彡
    1.30
    স
    1.27
     Engaging
    1.23
    स्यों
    1.23
     Harr
    1.16
     Ehe
    1.16
    ⵕ
    1.15
     ведь
    1.14
    Activations Density 0.260%

    No Known Activations