© 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. 8346
    Prev
    Next
    INDEX
    Explanations

    metal and metals

    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
    in
    1.74
    𝗴
    1.41
    um
    1.38
    م
    1.30
     νέα
    1.23
    ز
    1.15
    ം
    1.11
    в
    1.10
    ী
    1.10
    am
    1.09
    POSITIVE LOGITS
    ts
    1.30
    ’
    1.30
    }
    1.25
    tes
    1.14
    )
    1.13
    ]
    1.08
    1.04
    tt
    1.02
    ta
    0.95
    tti
    0.93
    Activations Density 0.034%

    No Known Activations