© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6178
    Prev
    Next
    INDEX
    Explanations

    business marketing and clients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    貅
    1.98
     ребята
    1.98
    adorable
    1.96
    可愛い
    1.95
     깜
    1.91
    Adorable
    1.91
     neuest
    1.90
     adorable
    1.89
    antoin
    1.88
     Mildred
    1.84
    POSITIVE LOGITS
    逆に
    1.96
     IMHO
    1.92
     whereas
    1.81
    むしろ
    1.71
     unless
    1.70
    一方で
    1.66
    걍
    1.64
     imo
    1.63
    そもそも
    1.61
     irrespective
    1.61
    Activations Density 0.436%

    No Known Activations