© 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. 109804
    Prev
    Next
    INDEX
    Explanations

    foraging for food

    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
    1
    0.89
    9
    0.86
    8
    0.84
    7
    0.76
    3
    0.74
     monasteries
    0.70
    ts
    0.68
    4
    0.67
    6
    0.67
    5
    0.67
    POSITIVE LOGITS
     يجب
    0.66
    р
    0.65
    бе
    0.64
    те
    0.61
     необходимо
    0.58
     werd
    0.58
     revel
    0.57
     провер
    0.57
    ся
    0.57
     pregunt
    0.57
    Activations Density 0.003%

    No Known Activations