© 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. 22049
    Prev
    Next
    INDEX
    Explanations

    delusion, present, promote, service, raising

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

    JSON structure and severity

    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
     Curl
    0.50
     hurts
    0.49
    拁
    0.49
     hurting
    0.48
     Worse
    0.45
     জার্সি
    0.42
     deserts
    0.42
     Нью
    0.41
     vyz
    0.41
    सिले
    0.40
    POSITIVE LOGITS
    ullivan
    0.45
    ≣
    0.44
     topologically
    0.43
    zel
    0.42
     graphically
    0.42
    ivamente
    0.41
    Fer
    0.41
    ')}
    0.41
    quasi
    0.40
    lii
    0.39
    Activations Density 0.000%

    No Known Activations