© 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-16K
    7. 10735
    Prev
    Next
    INDEX
    Explanations

    face, face, face

    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_16k_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
    0.54
    ène
    0.52
    urek
    0.47
    locals
    0.46
    izia
    0.46
     hygienic
    0.44
    oles
    0.44
     penetrate
    0.44
     bhavanti
    0.44
    höhe
    0.43
    POSITIVE LOGITS
     Menschen
    0.48
     modelli
    0.46
    DEFINITION
    0.44
    োহণ
    0.44
    氘
    0.43
     sujet
    0.43
    وجه
    0.43
     jedoch
    0.43
    ၿ
    0.42
     stijl
    0.41
    Activations Density 0.049%

    No Known Activations