© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58137
    Prev
    Next
    INDEX
    Explanations

    truth be uttered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一張
    -0.73
     Nachweis
    -0.73
     sobran
    -0.71
    Rol
    -0.70
    NATO
    -0.69
     daire
    -0.69
     tikra
    -0.69
    larında
    -0.69
    న్
    -0.69
     méxico
    -0.69
    POSITIVE LOGITS
     be
    4.66
     Be
    2.19
     будь
    2.14
    be
    2.11
    Be
    2.08
     быть
    1.86
     باشد
    1.70
     BE
    1.55
    beit
    1.51
     soient
    1.51
    Activations Density 0.018%

    No Known Activations