© 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. 240021
    Prev
    Next
    INDEX
    Explanations

    specific conditions or states

    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
    LinearLayout
    0.55
    generating
    0.54
    語
    0.53
    hairstyle
    0.49
    conducting
    0.48
    喈
    0.48
    只能
    0.47
    થે
    0.47
    felt
    0.47
    lecture
    0.47
    POSITIVE LOGITS
     loot
    0.54
     partie
    0.52
     boo
    0.52
     parti
    0.49
     koz
    0.49
     mik
    0.46
     VOT
    0.45
     păr
    0.44
     мя
    0.44
     lä
    0.43
    Activations Density 0.001%

    No Known Activations