© 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. 34048
    Prev
    Next
    INDEX
    Explanations

    instructions for boiling

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

    boil and simmer

    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
     muffin
    0.52
     choir
    0.49
     choirs
    0.48
    繍
    0.46
     PLUGIN
    0.46
     donn
    0.45
    াইব
    0.45
    <unused1>
    0.45
     modalità
    0.45
     vecin
    0.45
    POSITIVE LOGITS
     Boil
    0.80
     boil
    0.72
     boiled
    0.70
     boils
    0.65
     उबाल
    0.65
    煮
    0.58
     boiling
    0.56
    沸
    0.54
     Boiling
    0.53
    boiled
    0.51
    Activations Density 0.046%

    No Known Activations