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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3622
    Prev
    Next
    INDEX
    Explanations

    JSON structure code

    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_65k_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
     Wah
    0.75
     Edward
    0.73
     ED
    0.72
     Edwards
    0.71
     O
    0.70
     Wage
    0.68
     Comb
    0.68
     Gives
    0.66
     ACS
    0.66
     Electronic
    0.65
    POSITIVE LOGITS
     "":
    1.93
     '':
    1.83
     '*':
    1.56
     '/':
    1.48
    }:
    1.48
     '-':
    1.46
     _:
    1.37
    "":
    1.36
    $:
    1.31
    }));
    1.24
    Activations Density 0.122%

    No Known Activations