© 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. 28126
    Prev
    Next
    INDEX
    Explanations

    yao's, before the

    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
    s
    1.05
    "
    0.89
    ഞ
    0.81
    íticos
    0.78
    »
    0.78
    نس
    0.77
    ión
    0.77
    }$.
    0.77
    ség
    0.75
    "।
    0.72
    POSITIVE LOGITS
    <0x80>
    0.75
    า
    0.69
    za
    0.68
    _{
    0.67
     LABOR
    0.65
    c
    0.64
    ҝ
    0.64
    ۰
    0.64
    jir
    0.63
    ०
    0.63
    Activations Density 0.000%

    No Known Activations