© 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. 194138
    Prev
    Next
    INDEX
    Explanations

    specific questions and actions

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

    NAS, Node, bombing, character, list

    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
    ه
    0.52
    जू
    0.52
     पात्रता
    0.50
    puce
    0.50
     акаде
    0.50
    Org
    0.49
     beträgt
    0.49
    athan
    0.49
    াধ্য
    0.47
    㕝
    0.47
    POSITIVE LOGITS
     riconoscimento
    0.56
     homework
    0.49
    危険
    0.44
     risque
    0.44
     contenuti
    0.44
    לות
    0.43
     rischi
    0.43
    ן
    0.43
    বুদ্ধ
    0.43
     cambiamento
    0.43
    Activations Density 0.001%

    No Known Activations