© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 3445
    Prev
    Next
    INDEX
    Explanations

    mysterious and enigmatic descriptions

    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
    en
    1.85
    
    1.82
     расходов
    1.68
     emocional
    1.67
    sker
    1.65
    pwm
    1.64
    ს
    1.64
    ennem
    1.60
    隍
    1.58
    ಚ್ಚ
    1.56
    POSITIVE LOGITS
     colorido
    1.95
    ئی
    1.93
     potions
    1.83
     scarf
    1.77
     thriller
    1.76
    aziz
    1.74
    ঘরে
    1.72
    ﹍
    1.71
    ческий
    1.69
    𝑎
    1.68
    Activations Density 0.248%

    No Known Activations