© 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. 8240
    Prev
    Next
    INDEX
    Explanations

    github.com or github.io URLs

    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
    6
    0.82
    7
    0.82
    5
    0.79
    9
    0.77
    3
    0.76
    8
    0.70
     by
    0.70
    4
    0.70
    CELL
    0.66
    For
    0.64
    POSITIVE LOGITS
    0.68
     praticamente
    0.61
    ا
    0.61
     Telangana
    0.60
    <0x91>
    0.60
    ^*\
    0.58
     contenuto
    0.57
     powodu
    0.57
    ı
    0.54
    ierung
    0.53
    Activations Density 0.000%

    No Known Activations