© 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. 206
    Prev
    Next
    INDEX
    Explanations

    step-by-step explanations and conclusions

    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
     townhouse
    0.28
    kirche
    0.28
    boldsymbol
    0.27
    中に
    0.27
    мни
    0.26
    ลับ
    0.26
    夎
    0.26
    스러
    0.26
    swick
    0.25
    ))$.
    0.25
    POSITIVE LOGITS
    ad
    0.50
    ر
    0.46
    is
    0.43
    uk
    0.43
    ف
    0.42
    ed
    0.41
    ก
    0.41
    на
    0.40
    z
    0.39
    op
    0.39
    Activations Density 0.365%

    No Known Activations