© 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. 7091
    Prev
    Next
    INDEX
    Explanations

    identify specific 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
    ا
    3.32
    htub
    2.01
     তুল
    1.88
    “…
    1.88
    otene
    1.87
    اا
    1.81
    ্থ
    1.81
     toc
    1.81
    thers
    1.80
    ็ด
    1.80
    POSITIVE LOGITS
    𝙨
    2.93
    گزاری
    2.44
    𝙜
    2.41
    FirstResponder
    2.40
    디오
    2.39
    ουν
    2.39
    ὑ
    2.35
    ०
    2.34
    edian
    2.31
    ingos
    2.28
    Activations Density 0.435%

    No Known Activations