© 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. 6858
    Prev
    Next
    INDEX
    Explanations

    sub- prefixes and related concepts

    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
    y
    5.32
    ه
    5.17
    e
    5.10
    る
    5.01
    i
    4.99
    ে
    4.99
    a
    4.90
    ي
    4.69
    י
    4.66
    ۰
    4.57
    POSITIVE LOGITS
    琶
    2.51
    KindOfClass
    2.24
    𝚎
    2.15
    Попис
    2.10
    र्गत
    2.03
    𝚝
    1.95
    É
    1.93
    ष्णु
    1.93
    Il
    1.91
    匐
    1.91
    Activations Density 2.398%

    No Known Activations