© 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. 1685
    Prev
    Next
    INDEX
    Explanations

    `is` followed by topic 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
    י
    1.31
    Relationships
    1.20
     एवं
    1.13
     Relationships
    1.09
     وتح
    1.07
     globally
    1.07
     defining
    1.07
     стрем
    1.06
    ϋ
    1.05
    <unused502>
    1.04
    POSITIVE LOGITS
     cantar
    1.29
    ne
    1.25
     amarelo
    1.24
    numero
    1.23
    telefono
    1.23
    netje
    1.21
    telefone
    1.20
    耶
    1.20
    neho
    1.18
     sábado
    1.16
    Activations Density 1.783%

    No Known Activations