© 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. 128869
    Prev
    Next
    INDEX
    Explanations

    different skills, cultures, or things

    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
    ]^{+}$
    0.48
     undangan
    0.46
     tinnitus
    0.46
     গ্রাম
    0.44
     sejumlah
    0.43
     すご
    0.43
     मतदारसं
    0.43
    hamento
    0.43
     ghetto
    0.42
    鴿
    0.42
    POSITIVE LOGITS
    >:
    0.40
     differently
    0.39
     stiffer
    0.39
    odob
    0.39
    遇见
    0.38
     didn
    0.37
    aby
    0.37
     actions
    0.37
    {
    0.37
    سبة
    0.37
    Activations Density 0.013%

    No Known Activations