© 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. 9530
    Prev
    Next
    INDEX
    Explanations

    unlocking content

    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
     Ives
    0.89
     Pett
    0.87
     persons
    0.85
    neos
    0.84
    FrameworkElement
    0.83
    ausea
    0.83
    ᅨ
    0.83
    orer
    0.83
     emphasised
    0.83
    chromium
    0.82
    POSITIVE LOGITS
    ا
    1.00
     Unlock
    0.83
     unlock
    0.79
    unlock
    0.78
     unlocking
    0.74
    a
    0.74
    edition
    0.72
    ши
    0.72
     Onun
    0.72
    ا۔
    0.71
    Activations Density 0.175%

    No Known Activations