© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106767
    Prev
    Next
    INDEX
    Explanations

    compressor and compression

    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
     Pius
    0.60
    octet
    0.60
    ු
    0.58
    كم
    0.55
    וחות
    0.55
     dépl
    0.55
    പരമായ
    0.54
    ک
    0.54
    כם
    0.53
    _{+}\
    0.52
    POSITIVE LOGITS
    iph
    0.56
    oton
    0.50
    corrh
    0.49
    ixa
    0.49
    athu
    0.48
     personalidad
    0.47
    alg
    0.47
     مصرف
    0.47
     myel
    0.46
    als
    0.46
    Activations Density 0.004%

    No Known Activations