© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 5288
    Prev
    Next
    INDEX
    Explanations

    closer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_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
    an
    0.49
    ле
    0.46
    In
    0.41
     および
    0.41
    ஏ
    0.39
    azione
    0.39
    ananti
    0.39
    ,",
    0.39
    aus
    0.38
    .${
    0.37
    POSITIVE LOGITS
    0
    0.56
     
    0.55
     incroy
    0.45
    すごい
    0.42
     sueño
    0.42
     caminho
    0.40
    ק
    0.40
    Cadastro
    0.40
    리
    0.39
    사
    0.39
    Activations Density 9.926%

    No Known Activations