© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159202
    Prev
    Next
    INDEX
    Explanations

    specific terms following keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    mining gold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFORNIA
    0.55
    TransactionLog
    0.53
    你
    0.52
    u
    0.51
    Türkiye
    0.50
    油
    0.50
    اندا
    0.49
    維
    0.48
    Sono
    0.47
    だ
    0.47
    POSITIVE LOGITS
     COE
    0.52
     Severe
    0.51
     стреми
    0.50
     GAN
    0.49
    gean
    0.49
     BSC
    0.48
     κο
    0.47
    versions
    0.46
     Sapphire
    0.46
     SAE
    0.46
    Activations Density 0.001%

    No Known Activations