© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 10894
    Prev
    Next
    INDEX
    Explanations

    brushing, massage, soothe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ză
    1.42
    NCIA
    1.39
    ς
    1.34
    期
    1.26
    typeof
    1.24
    er
    1.21
    泪
    1.19
    єр
    1.16
    d
    1.15
    ously
    1.11
    POSITIVE LOGITS
    thebetterindia
    1.70
     разнообраз
    1.55
    JLabel
    1.53
    ګه
    1.44
    <unused2138>
    1.41
    boundingBox
    1.38
    HLIGHT
    1.37
     отмеча
    1.37
     developed
    1.32
    ിക
    1.30
    Activations Density 0.000%

    No Known Activations