© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47458
    Prev
    Next
    INDEX
    Explanations

    future iteration

    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_31_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
    쭌
    0.44
    Firstly
    0.43
     깜
    0.43
     firstly
    0.42
    ສະ
    0.42
     okaza
    0.42
    ከላ
    0.41
     Firstly
    0.41
     adjudged
    0.41
     eerste
    0.41
    POSITIVE LOGITS
    更大的
    0.40
    类
    0.38
    <sup>
    0.38
    ambahan
    0.36
    迭代
    0.36
    它们
    0.35
     类
    0.35
     eventualmente
    0.35
     کنه
    0.35
     ভবিষ্য
    0.35
    Activations Density 0.002%

    No Known Activations