© 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. 9671
    Prev
    Next
    INDEX
    Explanations

    building a nest

    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
    an
    1.66
    <0x80>
    1.43
    z
    1.41
    .
    1.41
    the
    1.33
    on
    1.27
    zelfde
    1.16
    é
    1.16
    ú
    1.14
    ం
    1.09
    POSITIVE LOGITS
     nests
    1.29
    EN
    1.23
    डी
    1.16
    UR
    1.11
     nest
    1.10
    त्र
    1.06
    логи
    1.05
     Nest
    1.05
    UDE
    1.03
     berths
    1.03
    Activations Density 0.004%

    No Known Activations