© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3814
    Prev
    Next
    INDEX
    Explanations

    that explains

    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_24_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
    ತರ
    0.60
     candles
    0.59
     reputed
    0.58
    ছিল
    0.57
     synthes
    0.57
     leagues
    0.57
    其
    0.56
     ailment
    0.56
     annihil
    0.55
     collinear
    0.55
    POSITIVE LOGITS
    zelfde
    0.94
     сегодняшний
    0.75
    ia
    0.73
    ları
    0.72
    Ngày
    0.72
    Ꭾ
    0.72
    Características
    0.71
    一方で
    0.70
    Questo
    0.69
     перегово
    0.69
    Activations Density 0.011%

    No Known Activations