© 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. 190945
    Prev
    Next
    INDEX
    Explanations

    selling water

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

    SAP CRM BOL

    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
    р
    0.60
    ικ
    0.49
    ர்
    0.49
    وك
    0.48
    誑
    0.48
    ен
    0.48
    ित
    0.47
    աս
    0.47
    स
    0.46
     কথায়
    0.46
    POSITIVE LOGITS
    ചെയ്യ
    0.52
    കൊണ്ട്
    0.48
    MORE
    0.48
    SWITCH
    0.47
     其实
    0.46
     Johnston
    0.46
     Toni
    0.46
     Going
    0.46
    MUX
    0.46
     Its
    0.46
    Activations Density 0.000%

    No Known Activations