© 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. 141844
    Prev
    Next
    INDEX
    Explanations

    aerobic capacity and fitness

    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
    侓
    0.63
    вает
    0.61
    ilibre
    0.60
    мага
    0.59
     entrenamiento
    0.59
     ಮಾಡುವ
    0.58
    гах
    0.57
    <unused2179>
    0.57
     elevada
    0.57
     alegria
    0.57
    POSITIVE LOGITS
    <0x0D>
    0.84
    </strong>
    0.68
    </sup>
    0.66
     Of
    0.57
     on
    0.55
    ยิน
    0.55
    Of
    0.54
    {
    0.54
    <0xF2>
    0.53
    Ralph
    0.53
    Activations Density 0.011%

    No Known Activations