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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14750
    Prev
    Next
    INDEX
    Explanations

    fine-orline

    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_17_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
    я
    3.42
    শালী
    3.19
    부터
    3.07
    можно
    2.90
    selectedIndex
    2.85
    morrow
    2.81
    𝑠
    2.76
    ял
    2.69
    拌
    2.65
     tela
    2.54
    POSITIVE LOGITS
    檎
    3.30
    felter
    2.98
    ナップ
    2.92
    backers
    2.91
    finity
    2.81
     staw
    2.77
    aments
    2.73
    venido
    2.68
    ayaran
    2.67
     motivo
    2.66
    Activations Density 1.069%

    No Known Activations