© 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. 127097
    Prev
    Next
    INDEX
    Explanations

    qualifications from

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

    government employee names

    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
    Pa
    0.52
    Rotating
    0.49
     Pa
    0.47
    ellite
    0.45
    也是
    0.43
    也能
    0.43
    ◆
    0.43
    íng
    0.43
    的生活
    0.42
    折
    0.42
    POSITIVE LOGITS
     freelancer
    0.52
     mutex
    0.50
     motherhood
    0.50
     spasm
    0.50
     ideia
    0.49
     freedoms
    0.48
     hazards
    0.48
     oryg
    0.48
     readership
    0.48
     йөк
    0.48
    Activations Density 0.003%

    No Known Activations