© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11451
    Prev
    Next
    INDEX
    Explanations

    changes made

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     also
    0.64
    めん
    0.57
     тоже
    0.55
     Also
    0.54
    also
    0.54
    <bos>
    0.54
    思想
    0.53
    "]
    0.53
    not
    0.53
    ]
    0.52
    POSITIVE LOGITS
     කිරීමට
    0.98
    𝒶
    0.98
    hk
    0.98
     artificially
    0.98
    앨
    0.96
     ລັບ
    0.95
     treten
    0.95
     대부분
    0.94
    उनकी
    0.94
     obej
    0.94
    Activations Density 0.025%

    No Known Activations