© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8990
    Prev
    Next
    INDEX
    Explanations

    words with repeated letters and numbers

    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_40_width_16k_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
     юриди
    0.42
     jurid
    0.40
     jurídico
    0.39
    köy
    0.39
     besieged
    0.38
    讥
    0.38
    耶路撒
    0.38
    锉
    0.37
    观点
    0.36
     ইংরেজি
    0.36
    POSITIVE LOGITS
     dir
    0.39
     JJ
    0.38
     corre
    0.38
    velopp
    0.35
     Corre
    0.35
     Yet
    0.35
     Lune
    0.35
    ،
    0.34
    Dir
    0.34
    Corre
    0.34
    Activations Density 0.113%

    No Known Activations