© 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. 205702
    Prev
    Next
    INDEX
    Explanations

    lucid daydream, dialog modes, cloud indexes

    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
     projection
    0.45
     perceptive
    0.43
     astron
    0.43
     j
    0.42
     ambush
    0.41
     sociable
    0.41
     kuliah
    0.40
     games
    0.40
     prospecting
    0.40
     $,
    0.40
    POSITIVE LOGITS
    stretch
    0.46
    María
    0.46
    égale
    0.46
    exemple
    0.46
    ázky
    0.45
    কিছু
    0.44
    œuvre
    0.43
    extérieur
    0.43
    pragma
    0.43
    adiya
    0.43
    Activations Density 0.005%

    No Known Activations