© 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. 155339
    Prev
    Next
    INDEX
    Explanations

    -ers plurals and job titles

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

    identity and actions

    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
     SalesLT
    0.49
     αυτές
    0.47
     Macmillan
    0.46
    arelli
    0.46
     Wharton
    0.46
     維
    0.45
     LU
    0.45
    akukan
    0.44
    Mac
    0.43
     MAC
    0.43
    POSITIVE LOGITS
     spectacularly
    0.53
    ៅ
    0.50
     murderers
    0.49
     defenders
    0.49
     worshippers
    0.48
     insurers
    0.47
     venezol
    0.47
     campaigners
    0.47
    ෞ
    0.46
    앰
    0.46
    Activations Density 0.000%

    No Known Activations