© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9101
    Prev
    Next
    INDEX
    Explanations

    programming and multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    𒄭
    0.44
    ጨማሪ
    0.42
     imidazole
    0.42
    ⚘
    0.42
     시작
    0.41
    垍
    0.41
    வச
    0.40
     ተጨማሪ
    0.40
    상
    0.39
     aven
    0.39
    POSITIVE LOGITS
    0
    0.47
    ellis
    0.40
     europeo
    0.38
    极
    0.38
    ляют
    0.38
    ấp
    0.38
     mesela
    0.38
    americana
    0.37
    chnitten
    0.37
     ocurrido
    0.37
    Activations Density 0.018%

    No Known Activations