© 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. 20756
    Prev
    Next
    INDEX
    Explanations

    unstated bias or automatic conversion

    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
    し
    1.07
     are
    1.02
    ある
    0.88
    我们
    0.87
     unidos
    0.82
    étaire
    0.80
     příjem
    0.79
     acus
    0.78
    0.78
    ה
    0.77
    POSITIVE LOGITS
    Implicit
    1.07
    ad
    1.04
     Implicit
    1.00
    FL
    1.00
     tacit
    0.93
    VF
    0.93
    VN
    0.91
    W
    0.91
     implicitly
    0.89
    Y
    0.88
    Activations Density 0.005%

    No Known Activations