© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15560
    Prev
    Next
    INDEX
    Explanations

    concentration of power

    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
    Not in Any Lists

    No Comments

    Negative Logits
    荕
    0.46
     imprisoned
    0.46
     pessoal
    0.46
     imprison
    0.45
     দাব
    0.45
     subdiv
    0.45
     hagan
    0.44
     sním
    0.44
    噱
    0.44
     usato
    0.44
    POSITIVE LOGITS
    م
    0.49
    耒
    0.45
     вас
    0.43
    オープ
    0.43
    at
    0.42
    вер
    0.42
     Explor
    0.42
    blocking
    0.42
     Reality
    0.42
     HOLDERS
    0.41
    Activations Density 0.007%

    No Known Activations