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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 17903
    Prev
    Next
    INDEX
    Explanations

    city metro systems

    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
    1
    1.05
    ного
    1.04
    3
    0.99
    ке
    0.94
    ﻭ
    0.94
    ADOS
    0.90
    8
    0.89
     были
    0.89
    6
    0.88
     plufieurs
    0.88
    POSITIVE LOGITS
    )
    1.33
    }
    1.14
    ]
    1.12
    ר
    0.97
     not
    0.96
    r
    0.95
     is
    0.94
     n
    0.90
     market
    0.87
    n
    0.86
    Activations Density 0.001%

    No Known Activations