Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 373
    Prev
    Next
    INDEX
    Explanations

    argument followed by closing punctuation

    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_29_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
    .')
    1.11
    .',
    0.93
    '.
    0.91
     '.')
    0.90
    `.
    0.88
     ".")
    0.87
    ’.
    0.85
    %.
    0.83
    !')
    0.81
    \".
    0.77
    POSITIVE LOGITS
    ):
    3.94
    "):
    3.63
     ):
    3.43
    ()):
    3.33
    '):
    3.32
    )):
    3.29
    ):
    3.24
    ]:
    3.17
    "]:
    3.16
    }:
    3.13
    Activations Density 0.950%

    No Known Activations