© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 31
    Prev
    Next
    INDEX
    Explanations

    integrated components

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

    payload generation or generator

    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
    骧
    0.45
    ൽക
    0.45
    стаў
    0.44
    煕
    0.44
    erb
    0.42
    Serv
    0.42
    дных
    0.41
    жела
    0.41
    孚
    0.41
    каў
    0.41
    POSITIVE LOGITS
     papill
    0.55
     uygulama
    0.54
     aplicando
    0.54
     приложение
    0.53
    lık
    0.51
     অন
    0.51
     عن
    0.50
     deforestation
    0.49
     किलो
    0.49
     aplik
    0.48
    Activations Density 0.000%

    No Known Activations