© 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. 186203
    Prev
    Next
    INDEX
    Explanations

    campaigns and Ralph Breaks

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

    buying or selling things

    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
    𝘻
    0.46
    lerden
    0.45
     veliki
    0.44
     loke
    0.43
    leri
    0.43
    স্বরূপ
    0.42
     ovog
    0.42
     Proces
    0.41
     kult
    0.41
    हरु
    0.41
    POSITIVE LOGITS
    侦
    0.49
     recognized
    0.49
    answered
    0.47
    偵
    0.47
     ಉತ್ತರ
    0.46
    Населення
    0.46
     recognizable
    0.46
     lured
    0.45
     ಅಭಿಮಾನ
    0.45
     reared
    0.45
    Activations Density 0.002%

    No Known Activations