© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 85817
    Prev
    Next
    INDEX
    Explanations

    passive income

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ě
    0.78
    ă
    0.76
     Untuk
    0.73
     deletes
    0.70
    所以
    0.69
    iva
    0.68
    ్య
    0.66
    anche
    0.66
    avan
    0.66
    ado
    0.65
    POSITIVE LOGITS
    Passive
    1.45
     passive
    1.45
     passively
    1.38
     Passive
    1.31
    passive
    1.30
    ing
    0.93
    ن
    0.82
    ре
    0.80
    }$=
    0.80
     निष्क्रिय
    0.75
    Activations Density 0.007%

    No Known Activations