© 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. 137995
    Prev
    Next
    INDEX
    Explanations

    Borussia Dortmund or bind mounts

    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
    ي
    0.66
    و
    0.64
    }/
    0.59
     Сасик
    0.59
    dauer
    0.57
    String
    0.56
    Nonce
    0.56
    σία
    0.55
    )};
    0.55
    rishna
    0.55
    POSITIVE LOGITS
    ینه
    0.59
    یل
    0.54
     muchos
    0.54
    的车
    0.53
    ین
    0.52
     sejumlah
    0.52
     perangkat
    0.52
    ди
    0.51
    ید
    0.51
     banyak
    0.51
    Activations Density 0.001%

    No Known Activations