© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4633
    Prev
    Next
    INDEX
    Explanations

    brand names and attributes

    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_17_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
     single
    0.78
    Single
    0.77
    д
    0.76
     good
    0.76
    otch
    0.75
    굴
    0.75
     처리
    0.75
     transformations
    0.73
    Cf
    0.72
    ghijkl
    0.72
    POSITIVE LOGITS
    name
    1.01
    𝐠
    0.91
    𝘨
    0.91
    াত্য
    0.88
     दौ
    0.88
    كة
    0.87
    ished
    0.87
     codice
    0.87
     arroz
    0.86
    namen
    0.86
    Activations Density 0.110%

    No Known Activations