© 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-262K
    7. 109568
    Prev
    Next
    INDEX
    Explanations

    correlation map

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ্ধু
    0.51
    ives
    0.49
    Ֆ
    0.46
    אה
    0.46
    dating
    0.45
    瓯
    0.44
    Ή
    0.42
    ótica
    0.41
    öt
    0.41
    '=>'','
    0.41
    POSITIVE LOGITS
    Dirs
    0.46
    Preference
    0.46
     timeout
    0.45
    就
    0.45
    SUPPORT
    0.45
     kèm
    0.45
     వారి
    0.43
    OfDeath
    0.42
     bloc
    0.41
    Support
    0.41
    Activations Density 0.004%

    No Known Activations