© 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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 120551
    Prev
    Next
    INDEX
    Explanations

    cling to things, people, or ideas

    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
    <0x80>
    0.93
    c
    0.92
    ně
    0.89
     свое
    0.83
    ),
    0.82
    ة
    0.81
    0
    0.79
    ط
    0.75
    alne
    0.74
    이라고
    0.73
    POSITIVE LOGITS
    ’
    1.22
    </h2>
    1.13
    1
    1.06
     cling
    1.02
    م
    1.02
    <0x0D>
    1.00
    </b>
    1.00
    </i>
    0.95
    </h3>
    0.94
     clinging
    0.92
    Activations Density 0.003%

    No Known Activations