© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1879
    Prev
    Next
    INDEX
    Explanations

    conjunctions and short words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     multiplicity
    1.51
    ر
    1.51
    Jika
    1.42
    ्स
    1.41
    ל
    1.40
    ר
    1.39
    ो
    1.39
    ට
    1.36
    ння
    1.33
    avacanam
    1.32
    POSITIVE LOGITS
    и
    1.14
    izabeth
    1.12
     собой
    1.12
    اقة
    1.09
     temer
    1.07
    тали
    1.07
     UInt
    1.06
    @]
    1.06
     Versailles
    1.04
     наблюда
    1.03
    Activations Density 0.028%

    No Known Activations