© 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. 1455
    Prev
    Next
    INDEX
    Explanations

    clues

    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
    es
    2.59
    \,\
    2.50
    ი
    2.24
    en
    2.23
    ی
    2.10
    ्स
    2.02
    i
    1.84
    }`,
    1.83
    esy
    1.81
    enje
    1.79
    POSITIVE LOGITS
     sekal
    1.54
    他们在
    1.48
    好評
    1.47
    вання
    1.45
     astrocytes
    1.45
    лябин
    1.42
    感じる
    1.32
    𝐫
    1.30
    ½
    1.30
     médic
    1.28
    Activations Density 0.537%

    No Known Activations