© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56303
    Prev
    Next
    INDEX
    Explanations

    indirect or indirectly

    np_acts-logits-general · gemini-2.5-flash-lite

    indirect or indirectly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     바로
    0.53
     그대로
    0.53
     autochtones
    0.52
     খাঁ
    0.51
     κο
    0.50
    ็ก
    0.50
    ！)
    0.49
    𝙪
    0.49
     Erwach
    0.49
    0
    0.49
    POSITIVE LOGITS
     Indirect
    1.20
     indirect
    1.19
    indirect
    1.18
    Indirect
    1.09
     indire
    1.03
     indirectly
    1.01
     INDIRECT
    0.98
     direct
    0.77
     directa
    0.74
     Direct
    0.72
    Activations Density 0.025%

    No Known Activations