© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99687
    Prev
    Next
    INDEX
    Explanations

    time to

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

    monitoring, observability, trends, derivatives, equipment

    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
    Not in Any Lists

    No Comments

    Negative Logits
    arlings
    0.55
     całej
    0.47
     introductions
    0.46
     author
    0.45
     penned
    0.45
    ែម
    0.45
    ∈</
    0.45
     отме
    0.44
     माझ्या
    0.44
    คาเดมี
    0.44
    POSITIVE LOGITS
    ْ
    0.55
    nya
    0.49
    ᒥ
    0.46
    符号
    0.44
     mismo
    0.44
    on
    0.44
    gameObject
    0.43
    ssh
    0.43
     dispositivo
    0.42
    외부
    0.42
    Activations Density 0.000%

    No Known Activations