© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 585
    Prev
    Next
    INDEX
    Explanations

    introducing examples or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    :
    0.57
    ：
    0.50
     :
    0.49
     ગયો
    0.49
     Notebook
    0.46
    ]:
    0.46
    我
    0.46
     =
    0.45
     Note
    0.45
    ]
    0.45
    POSITIVE LOGITS
     including
    1.52
     regardless
    1.37
     whether
    1.32
    including
    1.32
     especially
    1.26
     even
    1.23
     INCLUDING
    1.23
     irrespective
    1.19
     particularly
    1.19
     incluindo
    1.16
    Activations Density 0.828%

    No Known Activations