© 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. 56662
    Prev
    Next
    INDEX
    Explanations

    always or every

    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
     disturbs
    0.45
     disturbed
    0.39
     αρκε
    0.38
     někol
    0.38
     plufieurs
    0.38
    ζί
    0.37
     préf
    0.36
    𝒑
    0.36
     ид
    0.35
     запу
    0.35
    POSITIVE LOGITS
     always
    0.88
    always
    0.88
     ALWAYS
    0.86
    Always
    0.84
     siempre
    0.82
     всегда
    0.81
     Always
    0.80
    ALWAYS
    0.80
     every
    0.79
     selalu
    0.79
    Activations Density 0.177%

    No Known Activations