© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 116098
    Prev
    Next
    INDEX
    Explanations

    don't overdo it

    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
    Negative Logits
    u
    0.77
    ]
    0.75
    j
    0.75
    am
    0.69
    ad
    0.68
     ]
    0.68
    ing
    0.67
    }
    0.62
    is
    0.62
    a
    0.61
    POSITIVE LOGITS
     elegante
    0.64
    ك
    0.64
    رك
    0.61
     thuyền
    0.61
    󰡔
    0.60
    ຢ່າງ
    0.59
    عمل
    0.59
     beauties
    0.59
    ات
    0.59
     eloquence
    0.58
    Activations Density 0.008%

    No Known Activations