© 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. 31-GEMMASCOPE-2-RES-65K
    7. 31527
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    Negative Logits
    ኞ
    0.47
    vb
    0.45
    HOST
    0.41
    monds
    0.40
    ns
    0.39
    vista
    0.38
    WithFieldContext
    0.38
    သောအ
    0.38
    ｵ
    0.38
    xk
    0.38
    POSITIVE LOGITS
     ,
    0.54
     ]:
    0.53
     ]
    0.52
     ],
    0.51
     Weapon
    0.48
     ;
    0.46
     Maker
    0.46
     Creator
    0.43
     More
    0.42
     Parent
    0.42
    Activations Density 0.010%

    No Known Activations