© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104333
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    numerical values and specific words

    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
     prostředí
    0.44
    )+"
    0.44
    )^{*}\
    0.42
    ):\
    0.42
     \%,
    0.41
    enciais
    0.41
     credential
    0.41
    \"]
    0.41
     रैंकिंग
    0.41
    )}\
    0.41
    POSITIVE LOGITS
    麻烦
    0.46
    Aless
    0.44
    只有
    0.44
    Un
    0.42
    سا
    0.41
    خط
    0.41
     سود
    0.40
    阑
    0.40
     किफायती
    0.40
    Andre
    0.40
    Activations Density 0.001%

    No Known Activations