© 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. 8303
    Prev
    Next
    INDEX
    Explanations

    past and current roles

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

    career goals and experience

    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
     cuchar
    0.57
    使用
    0.55
    error
    0.51
     manchas
    0.51
     বিস্ম
    0.49
     spectrogram
    0.49
     vinaig
    0.48
    μ
    0.48
    螻
    0.48
    iccation
    0.47
    POSITIVE LOGITS
     freelance
    0.89
     freelancer
    0.77
     करियर
    0.76
     sabbatical
    0.76
     Career
    0.75
    転職
    0.75
    担任
    0.75
     Joining
    0.74
     career
    0.73
     Consulting
    0.72
    Activations Density 0.260%

    No Known Activations