© 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. 31-GEMMASCOPE-2-RES-65K
    7. 13343
    Prev
    Next
    INDEX
    Explanations

    int followed by identifier

    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_31_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
    '
    0.67
    ]
    0.65
    )
    0.59
     Alcohol
    0.58
     alcohol
    0.57
     '>
    0.57
     NSString
    0.57
     mają
    0.57
    の
    0.55
    вати
    0.54
    POSITIVE LOGITS
    t
    0.60
    ت
    0.59
    lah
    0.57
    lara
    0.56
    る
    0.54
     antal
    0.54
    number
    0.53
    PLEASE
    0.52
    lene
    0.51
    lika
    0.50
    Activations Density 0.033%

    No Known Activations