© 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. 19997
    Prev
    Next
    INDEX
    Explanations

    items

    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
     be
    1.41
    )
    1.20
    ли
    1.16
    (
    1.15
    什么
    1.12
    什么的
    1.10
    }
    1.06
     في
    1.05
    _
    1.00
     restaur
    0.96
    POSITIVE LOGITS
    ED
    1.23
    LA
    1.10
    AJ
    1.10
    on
    1.09
    DA
    1.08
    SD
    1.05
    AR
    1.03
    EA
    1.03
    AG
    1.02
     on
    1.00
    Activations Density 0.013%

    No Known Activations