© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 86080
    Prev
    Next
    INDEX
    Explanations

    billions and millions of users

    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
    urile
    0.71
     Nhiều
    0.61
     fleste
    0.60
    eni
    0.60
    umni
    0.59
    é
    0.59
    lni
    0.59
    ási
    0.57
    icole
    0.57
              
    0.56
    POSITIVE LOGITS
    },
    0.58
    드
    0.54
    】,
    0.54
     არ
    0.53
    ),
    0.53
     housekeeping
    0.52
     indulgent
    0.52
     tranquila
    0.52
    ст
    0.51
    다면
    0.51
    Activations Density 0.024%

    No Known Activations