© 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. 13552
    Prev
    Next
    INDEX
    Explanations

    indirectly or proxy

    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
     occurrence
    0.39
    esse
    0.38
    jPanel
    0.38
     replacement
    0.37
     intentional
    0.37
     deliberate
    0.37
     താ
    0.37
     MFA
    0.36
    啄
    0.36
     various
    0.35
    POSITIVE LOGITS
     indirectly
    0.97
    Indirect
    0.76
     INDIRECT
    0.74
     indire
    0.73
     Indirect
    0.72
    indirect
    0.71
     indirect
    0.65
     extrapolate
    0.63
     proxy
    0.60
     transferable
    0.58
    Activations Density 0.425%

    No Known Activations