© 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. 40-GEMMASCOPE-2-RES-65K
    7. 56064
    Prev
    Next
    INDEX
    Explanations

    human faces and voices

    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_40_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
    ("%
    0.46
     affecting
    0.42
    ('%
    0.41
    ール
    0.39
     italics
    0.39
    Affect
    0.38
    自分の
    0.38
     आपल्या
    0.38
     svom
    0.38
    ]".
    0.38
    POSITIVE LOGITS
     humana
    0.51
    धारी
    0.51
     humano
    0.48
     właścic
    0.47
     holder
    0.46
     familiar
    0.46
     owners
    0.45
     trẻ
    0.45
    owners
    0.45
     owner
    0.45
    Activations Density 0.045%

    No Known Activations