© 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. 136536
    Prev
    Next
    INDEX
    Explanations

    large numbers and ordinals

    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
     понял
    0.41
     قلنا
    0.40
    sole
    0.38
     रेपो
    0.38
     ላ
    0.37
     Best
    0.37
     Nokia
    0.37
    ことができます
    0.37
     Primary
    0.36
    urls
    0.36
    POSITIVE LOGITS
    kbeta
    0.47
    Kabhi
    0.39
     insuff
    0.39
    Chiều
    0.39
     impi
    0.39
    stände
    0.38
    gebäude
    0.38
    oluene
    0.38
    রাশ
    0.38
    ח
    0.38
    Activations Density 0.003%

    No Known Activations