© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 103529
    Prev
    Next
    INDEX
    Explanations

    possession of skills or experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
     possession
    0.96
     Possession
    0.87
     a
    0.86
    та
    0.81
    ль
    0.81
    िकता
    0.78
     apresent
    0.77
     produ
    0.71
    yb
    0.71
    ле
    0.71
    POSITIVE LOGITS
    ৮
    0.85
    。
    0.84
    ৯
    0.80
    7
    0.76
    0
    0.75
    もっと
    0.75
    9
    0.74
    ors
    0.73
    ist
    0.73
    }/>
    0.70
    Activations Density 0.004%

    No Known Activations