© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10873
    Prev
    Next
    INDEX
    Explanations

    Elo rating system

    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_7_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
    s
    4.81
    sman
    3.60
    sí
    3.52
    sion
    3.50
    e
    3.39
    t
    3.35
    ה
    3.33
    sels
    3.26
    eek
    3.25
    ei
    3.22
    POSITIVE LOGITS
    сть
    2.56
    ैर
    2.50
    ር
    2.40
    udent
    2.40
    ça
    2.38
    ēs
    2.37
    奘
    2.33
    𝚘
    2.29
    othesis
    2.27
    ڈن
    2.26
    Activations Density 0.010%

    No Known Activations