© 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. 13-GEMMASCOPE-2-RES-16K
    7. 16101
    Prev
    Next
    INDEX
    Explanations

    hopeful tone or vision

    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_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
    য়ের
    2.71
    𝗺
    2.70
     mắn
    2.64
    𝗼
    2.60
    𝗮
    2.58
    𝒖
    2.55
    絊
    2.53
    𝘂
    2.49
    𝗻
    2.48
    𝗹
    2.45
    POSITIVE LOGITS
    𝑠
    2.47
    an
    2.41
    حال
    2.20
    ان
    2.11
    is
    2.10
    ikis
    2.10
    وض
    2.08
     ‘
    2.05
    lauf
    2.04
    fung
    2.03
    Activations Density 0.107%

    No Known Activations