© 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. 9234
    Prev
    Next
    INDEX
    Explanations

    bath bomb or bath salts

    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
    the
    1.20
    The
    1.13
    á
    1.09
    ت
    1.02
    t
    1.01
    c
    1.00
    1
    0.98
    an
    0.93
    т
    0.93
    z
    0.92
    POSITIVE LOGITS
     bath
    0.92
     }>
    0.86
     Bath
    0.84
     baths
    0.84
     for
    0.83
     }{\
    0.83
     }^{
    0.80
    ↵↵
    0.79
    內的
    0.79
    ন
    0.78
    Activations Density 0.003%

    No Known Activations