© 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. 156921
    Prev
    Next
    INDEX
    Explanations

    engaging in programs and services

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

    mode, shelter, or individuals

    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
     받은
    0.50
     ጭ
    0.45
    받
    0.45
    ponente
    0.45
    㑼
    0.45
     वर्
    0.44
     कोरिया
    0.44
     नियो
    0.44
    ]+")
    0.43
    ፫
    0.43
    POSITIVE LOGITS
     levies
    0.52
     assists
    0.50
     butcher
    0.50
     levels
    0.49
     exercises
    0.49
     proteins
    0.49
     Hannibal
    0.49
     te
    0.48
     accelerators
    0.48
     cycles
    0.48
    Activations Density 0.001%

    No Known Activations